Foundation pit soil layer mechanical parameter back analysis method and system

Through the comparison and correction of ground survey data and monitoring data, soil parameters are adjusted, and the problem of the inverse analysis method of the foundation pit soil layer mechanical parameters in the existing technology relying on a large amount of time sequence data, and the accurate surrounding rock data is achieved during construction and optimize construction design.

CN119026410APending Publication Date: 2024-11-26新疆铁道勘察设计院有限公司

Patent Information

Application Number
CN202411085986.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing inverse analysis method for soil layer mechanical parameters in foundation pit requires a large amount of time series data to obtain more accurate analysis results and prediction results, and cannot be corrected through real-time monitoring data, resulting in unsatisfactory calculation results.

Method used

By obtaining the ground survey data of the target foundation pit area, strata stratification, sampling and obtaining soil parameters, establishing a finite element model, combining actual monitoring data and simulation monitoring data to calculate similarity, and adjusting soil parameters until the similarity is less than the preset Value, complete the inverse analysis of soil parameters.

Benefits of technology

Comparison and correction based on actual monitoring data is realized, and relatively accurate surrounding rock data is obtained, which can guide the support plan during construction and provide accurate stratigraphic data, and optimize the construction design.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026410A_ABST
    Figure CN119026410A_ABST
Patent Text Reader

Abstract

The invention discloses a foundation pit soil layer mechanical parameter back analysis method and system. The method comprises the steps that stratigraphic stratification data are obtained; acquiring soil parameters of different stratums; establishing a finite element model, and obtaining a working condition; actual monitoring data of the target foundation pit area are obtained, and simulation monitoring data are obtained through simulation calculation; after the soil parameters are adjusted, new simulation monitoring data and similarity data are obtained through recalculation, and when the soil parameters are repeatedly adjusted till the similarity data are smaller than a preset value, the soil parameters serve as soil parameters of the stratum corresponding to the current working condition; finally, the adjusted soil body parameters serve as stratum data. According to the foundation pit soil layer mechanical parameter back analysis method and system, through the technical scheme, based on comparison and correction with actual monitoring data, accurate surrounding rock data can be obtained, instructive data can be provided for a supporting scheme in construction, and the construction efficiency is improved. And accurate stratum data can be provided for projects in the same batch for design and construction optimization.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of soil layer mechanics analysis, and in particular, relates to a method and system for inverse analysis of mechanical parameters of foundation pit soil layers. Background Art

[0002] Foundation pit construction is a construction method in civil engineering, which mainly involves the excavation of basements and underground structures (such as subways, tunnels, underground garages, etc.) in construction projects. The purpose of foundation pit construction is to provide space for the construction of underground structures while ensuring the safety of the construction process and the stability of the surrounding environment. Foundation pit back analysis is a method that uses measured data to determine the mechanical parameters and constitutive model of soil. It has important applications in soil displacement prediction and foundation pit engineering.

[0003] In the Chinese patent application number 202311663133.2, an intelligent early warning monitoring method for deep foundation pit construction adjacent to the subway based on BP neural network and numerical analysis is disclosed, including: establishing a finite element model; using the BP neural network to inversely calculate the soil parameters of the finite element model based on the on-site preliminary construction monitoring data, and correcting the finite element model; using the corrected finite element model to simulate the foundation pit excavation process according to the construction plan, and combining the monitoring data to find out the potential dangerous points of the subway line and the foundation pit support during the construction process; constructing a BP neural network time series model based on the preliminary monitoring data of the dangerous point, and inferring the deformation development of the dangerous point in the future period of time, so as to achieve early control and early warning.

[0004] The defect in the existing technology is that, in practical applications, the BP neural network requires a large amount of time series data for training in order to obtain more accurate analysis and prediction results. The data obtained during the construction process is often insufficient to support model training, and the data calculated by numerical calculations is affected by the corresponding numerical values ​​of the model, and the calculation results will also be unsatisfactory. Summary of the invention

[0005] In view of the problem that the existing inverse analysis method of mechanical parameters of foundation pit soil layers requires a large amount of time series data for training in order to obtain relatively accurate analysis results and prediction results, and is unable to obtain accurate surrounding rock data through comparison and correction of real-time monitoring data, the present invention provides a inverse analysis method and system for mechanical parameters of foundation pit soil layers.

[0006] In order to achieve the above technical objectives, the technical solution adopted by the present invention is as follows:

[0007] A back analysis method for mechanical parameters of foundation pit soil layer, comprising:

[0008] Acquire geological survey data of the target foundation pit area, and perform stratigraphic stratification on the target foundation pit area according to the geological survey data to obtain stratigraphic stratification data;

[0009] According to the stratigraphic stratification data, each stratum in the target foundation pit area is sampled respectively, and experiments are carried out to obtain soil parameters of different strata; the soil parameters include internal friction angle, cohesion, elastic modulus and Poisson's ratio;

[0010] A finite element model is established based on the stratigraphic layer data and soil parameters, and the excavation and support process of each layer in the stratigraphic layer data is taken as a working condition;

[0011] When excavating the target foundation pit area, when excavation and support of a working condition are completed, the actual monitoring data of the target foundation pit area is obtained, and the working condition is simulated and calculated by the finite element model to obtain simulation monitoring data;

[0012] The actual monitoring data and the simulated monitoring data both include the vertical displacement of the ground surface, the deep displacement of the support structure corresponding to the working condition, and the internal force of the support structure corresponding to the working condition, and the monitoring points of the actual monitoring data and the simulated monitoring data correspond;

[0013] The similarity between the simulated monitoring data and the actual monitoring data is calculated as similarity data, and the soil parameters of the stratum corresponding to the current working condition in the finite element model are adjusted and then recalculated to obtain new simulated monitoring data;

[0014] Calculate new similarity data based on the new simulation monitoring data and the actual monitoring data, and repeatedly adjust the soil parameters for simulation calculation until the similarity data is less than a preset value, and use the corresponding soil parameters as the soil parameters of the stratum corresponding to the current working condition;

[0015] The foundation pit excavation, finite element simulation calculation and soil parameter adjustment are repeated until the foundation pit excavation of the target foundation pit area is completed, and the soil parameters of all strata finally adjusted are used as the stratum data of the target foundation pit area.

[0016] A foundation pit soil mechanical parameter back analysis system, comprising:

[0017] An acquisition unit is configured to acquire geological survey data of a target foundation pit area, and perform stratigraphic stratification on the target foundation pit area according to the geological survey data to form stratigraphic stratification data;

[0018] The test unit is configured to sample each stratum in the target foundation pit area according to the stratum stratification data and conduct tests to obtain soil parameters of different strata; the soil parameters include internal friction angle, cohesion, elastic modulus and Poisson's ratio;

[0019] A modeling unit is configured to establish a finite element model according to the stratum layering data and the soil parameters, and to regard the excavation and support process of each stratum in the stratum layering data as a working condition;

[0020] The computing unit is configured as:

[0021] When excavating the target foundation pit area, actual monitoring data of the target foundation pit area is obtained when excavation and support of one working condition are completed, and simulation calculation of the working condition is performed through the finite element model to obtain simulation monitoring data; the actual monitoring data and the simulation monitoring data both include surface vertical displacement, deep displacement of the support structure corresponding to the working condition, and internal force of the support structure corresponding to the working condition, and the monitoring points of the actual monitoring data and the simulation monitoring data correspond;

[0022] Calculating the similarity between the simulated monitoring data and the actual monitoring data as similarity data, and adjusting the soil parameters of the stratum corresponding to the current working condition in the finite element model and recalculating to obtain new simulated monitoring data;

[0023] Calculating new similarity data according to the new simulation monitoring data and the actual monitoring data, and repeatedly adjusting the soil parameters for simulation calculation until the similarity data is less than a preset value, and using the corresponding soil parameters as the soil parameters of the stratum corresponding to the current working condition;

[0024] The foundation pit excavation, finite element simulation calculation and soil parameter adjustment are repeated until the foundation pit excavation of the target foundation pit area is completed, and the soil parameters of all strata that have been finally adjusted are used as stratum data of the target foundation pit area.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] Through the above technical scheme, more accurate surrounding rock data can be obtained based on comparison and correction with actual monitoring data, which can not only provide guiding data for support schemes during construction, but also provide accurate formation data for the same batch of projects for design and construction optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 The present invention is an overall flow chart of a method for back-analyzing mechanical parameters of a foundation pit soil layer in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to facilitate the understanding of those skilled in the art, the present invention is further described below in conjunction with embodiments and drawings. The contents mentioned in the implementation modes are not intended to limit the present invention.

[0029] like Figure 1 As shown, this embodiment provides a method for back-analyzing mechanical parameters of foundation pit soil layers, which may specifically include the contents described in the following steps S1 to S7.

[0030] S1: acquiring geological survey data of a target foundation pit area, and performing stratigraphic stratification on the target foundation pit area according to the geological survey data to form stratigraphic stratification data;

[0031] S2: sampling each stratum in the target foundation pit area according to the stratum stratification data and conducting tests to obtain soil parameters of different strata; the soil parameters include internal friction angle, cohesion, elastic modulus and Poisson's ratio;

[0032] S3: establishing a finite element model according to the stratum layering data and the soil parameters, and taking the excavation and support process of each stratum in the stratum layering data as a working condition;

[0033] S4: when excavating the target foundation pit area, obtaining actual monitoring data of the target foundation pit area when completing excavation and support of one working condition, and performing simulation calculation on the working condition through the finite element model to obtain simulation monitoring data; the actual monitoring data and the simulation monitoring data both include surface vertical displacement, deep displacement of the support structure corresponding to the working condition, and internal force of the support structure corresponding to the working condition, and the monitoring points of the actual monitoring data and the simulation monitoring data correspond;

[0034] S5: calculating the similarity between the simulation monitoring data and the actual monitoring data as similarity data, and adjusting the soil parameters of the stratum corresponding to the current working condition in the finite element model and recalculating to obtain new simulation monitoring data;

[0035] S6: calculating new similarity data according to the new simulation monitoring data and the actual monitoring data, and repeatedly adjusting the soil parameters for simulation calculation until the similarity data is less than a preset value, and using the corresponding soil parameters as the soil parameters of the stratum corresponding to the current working condition;

[0036] S7: Repeat the foundation pit excavation, finite element simulation calculation and soil parameter adjustment until the foundation pit excavation of the target foundation pit area is completed, and the soil parameters of all strata that are finally adjusted are used as stratum data of the target foundation pit area.

[0037] When implementing the embodiments of the present application, it is necessary to first obtain geological survey data through on-site investigation, and the acquisition process can be carried out by drilling and other methods. The geological survey data will characterize the approximate distribution of the strata, but as the construction proceeds, the surrounding rock related parameters will also change with the process of stress release. The main purpose of the embodiments of the present application is to calculate the changed surrounding rock parameters for design correction and other related project construction. In the embodiments of the present application, the strata can be layered through geological survey data for subsequent modeling. Samples of each layer are sampled by drilling and corresponding tests are carried out to obtain the internal friction angle, cohesion, elastic modulus and Poisson's ratio.

[0038] In the embodiments of the present application, after constructing the finite element model, it is necessary to select the corresponding constitutive model, which belongs to the prior art and is not limited in the embodiments of the present application; and in order to realize the simulation of the excavation process, the excavation and support process of each stratum layer is taken as a working condition, and each working condition is calculated on the basis of the completion of the previous working condition. In this way, when calculating each working condition, the relevant parameters of the stratum corresponding to the working condition can be more accurately inverted and analyzed. After completing the finite element modeling, it is necessary to collect data during the construction process. It should be understood that the actual monitoring data obtained by monitoring and the simulation monitoring data obtained by the finite element model calculation should be in a corresponding relationship, that is, the monitored parts should be the same, and the collected data should also be the same. The collected data needs to include at least the vertical displacement of the surface, the deep displacement of the support structure, and the internal force of the support structure.

[0039] In the embodiment of the present application, in order to determine the difference between the current simulation situation and the actual monitoring data, the difference is evaluated by similarity data, and the difference between different data streams can be calculated by similarity through a variety of technologies in the prior art, and the embodiment of the present application is not limited. At the same time, the soil parameters are adjusted and the new simulation monitoring data is recalculated, and the similarity data is calculated again for evaluation until the similarity between the simulation monitoring data and the actual monitoring data in the current round reaches a certain degree. At this time, the corresponding soil parameters are recorded, and the next round of foundation pit excavation, finite element simulation calculation and soil parameter adjustment cycle are performed; it should be understood that each round corresponds to the excavation of a stratum, and also corresponds to a working condition, and the result of the soil parameters finally formed will also correspond to the stratum. When the accurate soil parameters are obtained after each working condition calculation, it is necessary to assign the soil parameters to the corresponding stratum in the finite element model for subsequent calculation. Through the above-mentioned technical solution, the embodiment of the present application can obtain more accurate surrounding rock data based on the comparison and correction with the actual monitoring data, which can not only provide guiding data for the support scheme during construction, but also provide accurate stratum data for the same batch of projects for design and construction optimization.

[0040] In a possible implementation, performing stratigraphic stratification on the target foundation pit area according to the geological survey data to form stratigraphic stratification data includes:

[0041] Obtaining the buried depth of the stratum boundary from the geological survey data;

[0042] The target foundation pit area is stratigraphically layered according to the burial depth.

[0043] When the embodiments of the present application are implemented, the strata can be stratified according to the burial depth of different strata, and further subdivided according to the design and construction plan. For example, further subdivided according to the construction stratification in the design and construction plan can ensure the consistency of strata stratification and construction progress.

[0044] In a possible implementation, the calculation of the similarity data includes:

[0045] The simulation monitoring data is vectorized to form a first vector, and the actual monitoring data is vectorized to form a second vector; the elements in the first vector and the second vector both include the ground surface vertical displacement value, the deep displacement value of the support structure and the internal force value of the support structure;

[0046] A cosine distance between the first vector and the second vector is calculated, and the cosine distance is used as the similarity data.

[0047] When implementing the embodiment of the present application, cosine similarity is preferably used to calculate the similarity data, and the calculation process is relatively simple. It should be understood that the first vector and the second vector described in the embodiment of the present application are high-dimensional vectors, which can contain a variety of monitoring data. The surface vertical displacement value, the deep displacement value of the support structure and the internal force value of the support structure are only part of the data contained therein.

[0048] In a possible implementation, adjusting the soil parameters of the stratum corresponding to the current working condition in the finite element model includes:

[0049] Inputting the soil mass parameter into a preset generation model, and receiving a first soil mass parameter output by the generation model;

[0050] The first soil mass parameter is input into a preset recognition model, and when an output result of the recognition model is true, the first soil mass parameter is used as the adjusted soil mass parameter.

[0051] In a possible implementation, inputting the soil parameter into a preset generation model, and receiving the first soil parameter output by the generation model includes:

[0052] Obtaining the surrounding rock lithology corresponding to the soil mass parameters, and obtaining the upper and lower bounds of the soil mass parameters corresponding to the surrounding rock lithology;

[0053] The generation model uses the value of the soil parameter as the average value and uses the value closest to the value of the soil parameter between the upper bound and the lower bound as the distribution boundary to construct a standard normal distribution function;

[0054] The generation model outputs the first soil parameter according to the probability distribution of the standard normal distribution function.

[0055] When implementing the embodiment of the present application, in order to reduce the randomness in the process of generating soil parameters, the soil parameters are generated by constructing a standard normal distribution, wherein the soil parameters correspond to different surrounding rock lithologies, and the corresponding relationship can be obtained from geological survey data. The corresponding soil parameters of different surrounding rocks will have a certain data range, and the upper and lower bounds of the data range are used to generate a standard normal distribution function; using the value in the current soil parameter as the average value can make the randomly generated soil parameter appear near the current soil parameter with a greater probability, reducing the discreteness of the data. In the embodiment of the present application, when constructing the standard normal distribution function, the value in the upper and lower bounds closest to the value in the soil parameter is used as the boundary value, which can further compress the random space, reduce the discreteness of the data, and make the generated results less offset.

[0056] In a possible implementation manner, inputting the first soil parameter into a preset recognition model, and using the first soil parameter as the adjusted soil parameter when an output result of the recognition model is true includes:

[0057] Obtaining a shear strength range and a shear modulus range corresponding to the surrounding rock lithology according to the surrounding rock lithology;

[0058] The identification model calculates the expected shear strength according to the internal friction angle and the cohesion in the first soil mass parameter, and calculates the expected shear modulus according to the elastic modulus and the Poisson's ratio in the first soil mass parameter;

[0059] When the expected shear strength falls within the shear strength range, and the expected shear modulus falls within the shear modulus range, the identification model outputs a true result.

[0060] When the embodiment of the present application is implemented, the corresponding first soil parameter generated needs to meet the relevant properties of the current surrounding rock lithology, among which at least Mohr's Coulomb criterion and Hooke's law need to be met; for Mohr's Coulomb criterion, for the same surrounding rock lithology, the shear strength will be within a range, that is, the shear strength range, and the shear strength can be calculated by the internal friction angle and the cohesion. If the calculated shear strength is within the shear strength range, it means that the current first soil parameter meets Mohr's Coulomb criterion; similarly, for Hooke's law, for the same surrounding rock lithology, the shear modulus will be within a range, that is, the shear modulus range, and the shear modulus can be calculated by the elastic modulus and Poisson's ratio. If the calculated shear modulus is within the shear modulus range, it means that the current first soil parameter meets Hooke's law; it should be understood that the elastic modulus described in the embodiment of the present application is Young's modulus. By verifying Mohr's Coulomb criterion and Hooke's law, it can be ensured that the generated first soil parameter is within the correct range.

[0061] The present application also provides a foundation pit soil mechanical parameter back analysis system, including:

[0062] An acquisition unit is configured to acquire geological survey data of a target foundation pit area, and perform stratigraphic stratification on the target foundation pit area according to the geological survey data to form stratigraphic stratification data;

[0063] The test unit is configured to sample each stratum in the target foundation pit area according to the stratum stratification data and conduct tests to obtain soil parameters of different strata; the soil parameters include internal friction angle, cohesion, elastic modulus and Poisson's ratio;

[0064] A modeling unit is configured to establish a finite element model according to the stratum layering data and the soil parameters, and to regard the excavation and support process of each stratum in the stratum layering data as a working condition;

[0065] The computing unit is configured as:

[0066] When excavating the target foundation pit area, actual monitoring data of the target foundation pit area is obtained when excavation and support of one working condition are completed, and simulation calculation of the working condition is performed through the finite element model to obtain simulation monitoring data; the actual monitoring data and the simulation monitoring data both include surface vertical displacement, deep displacement of the support structure corresponding to the working condition, and internal force of the support structure corresponding to the working condition, and the monitoring points of the actual monitoring data and the simulation monitoring data correspond;

[0067] Calculating the similarity between the simulated monitoring data and the actual monitoring data as similarity data, and adjusting the soil parameters of the stratum corresponding to the current working condition in the finite element model and recalculating to obtain new simulated monitoring data;

[0068] Calculating new similarity data according to the new simulation monitoring data and the actual monitoring data, and repeatedly adjusting the soil parameters for simulation calculation until the similarity data is less than a preset value, and using the corresponding soil parameters as the soil parameters of the stratum corresponding to the current working condition;

[0069] The foundation pit excavation, finite element simulation calculation and soil parameter adjustment are repeated until the foundation pit excavation of the target foundation pit area is completed, and the soil parameters of all strata that have been finally adjusted are used as stratum data of the target foundation pit area.

[0070] In a possible implementation manner, the acquiring unit is further configured to:

[0071] Obtaining the buried depth of the stratum boundary from the geological survey data;

[0072] The target foundation pit area is stratigraphically layered according to the burial depth.

[0073] In a possible implementation manner, the computing unit is further configured to:

[0074] The simulation monitoring data is vectorized to form a first vector, and the actual monitoring data is vectorized to form a second vector; the elements in the first vector and the second vector both include the ground surface vertical displacement value, the deep displacement value of the support structure and the internal force value of the support structure;

[0075] A cosine distance between the first vector and the second vector is calculated, and the cosine distance is used as the similarity data.

[0076] In a possible implementation manner, the computing unit is further configured to:

[0077] Inputting the soil mass parameter into a preset generation model, and receiving a first soil mass parameter output by the generation model;

[0078] The first soil mass parameter is input into a preset recognition model, and when an output result of the recognition model is true, the first soil mass parameter is used as the adjusted soil mass parameter.

[0079] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0080] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0081] The units described as separate components may or may not be physically separated. As units, it is obvious that a person of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0082] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0083] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a grid device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0084] The above is a detailed introduction to a back analysis method and system for mechanical parameters of foundation pit soil provided by the present application. The description of the specific embodiment is only used to help understand the method and its core idea of ​​the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.

Claims

1. A method for back analysis of mechanical parameters of foundation pit soil layer, characterized in that: Includes steps: Acquire geological survey data of the target foundation pit area, and perform stratigraphic stratification on the target foundation pit area according to the geological survey data to obtain stratigraphic stratification data; According to the stratigraphic stratification data, each stratum in the target foundation pit area is sampled separately, and experiments are carried out to obtain the soil parameters of different strata; A finite element model is established based on the stratigraphic layer data and soil parameters, and the excavation and support process of each layer in the stratigraphic layer data is taken as a working condition; When excavating the target foundation pit area, when excavation and support of a working condition are completed, the actual monitoring data of the target foundation pit area is obtained, and the working condition is simulated and calculated by the finite element model to obtain simulation monitoring data; The similarity between the simulated monitoring data and the actual monitoring data is calculated as similarity data, and the soil parameters of the stratum corresponding to the current working condition in the finite element model are adjusted and then recalculated to obtain new simulated monitoring data; Calculate new similarity data based on the new simulation monitoring data and the actual monitoring data, and repeatedly adjust the soil parameters for simulation calculation until the similarity data is less than a preset value, and use the corresponding soil parameters as the soil parameters of the stratum corresponding to the current working condition; The foundation pit excavation, finite element simulation calculation and soil parameter adjustment are repeated until the foundation pit excavation of the target foundation pit area is completed, and the soil parameters of all strata finally adjusted are used as the stratum data of the target foundation pit area.

2. A method for back analysis of mechanical parameters of foundation pit soil layer according to claim 1, characterized in that: According to the geological survey data, the target foundation pit area is stratigraphically layered, and the stratigraphic layering data formed include: Obtain the buried depth of the stratigraphic boundary from geological survey data; The target foundation pit area is stratigraphically stratified according to the burial depth.

3. A method for back analysis of mechanical parameters of foundation pit soil layer according to claim 2, characterized in that: The calculation of similarity data includes: Vectorizing the simulated monitoring data to form a first vector, and vectorizing the actual monitoring data to form a second vector; The elements in the first vector and the second vector both include the ground surface vertical displacement value, the deep displacement value of the supporting structure and the internal force value of the supporting structure; A cosine distance between the first vector and the second vector is calculated, and the cosine distance is used as similarity data.

4. A method for back analysis of mechanical parameters of foundation pit soil layer according to claim 3, characterized in that: Soil parameters include internal friction angle, cohesion, elastic modulus and Poisson’s ratio; Adjusting the soil parameters of the stratum corresponding to the current working conditions in the finite element model includes: Inputting soil parameters into a preset generation model, and receiving first soil parameters output by the generation model; The first soil parameter is input into a preset recognition model, and when an output result of the recognition model is true, the first soil parameter is used as the adjusted soil parameter.

5. A method for back analysis of mechanical parameters of foundation pit soil layer according to claim 4, characterized in that: Inputting soil parameters into a preset generation model and receiving first soil parameters output by the generation model includes: Obtaining the surrounding rock lithology corresponding to the soil parameters, and obtaining the upper and lower bounds of the soil parameters corresponding to the surrounding rock lithology; The generation model takes the value in the soil parameter as the average value and the value closest to the value in the soil parameter in the upper and lower bounds as the distribution boundary to construct the standard normal distribution function; The generation model outputs a first soil parameter according to the probability distribution of the standard normal distribution function.

6. A method for back analysis of mechanical parameters of foundation pit soil layer according to claim 5, characterized in that: Inputting the first soil parameter into a preset identification model, and using the first soil parameter as the adjusted soil parameter when an output result of the identification model is true includes: Obtain the shear strength range and shear modulus range corresponding to the surrounding rock lithology according to the surrounding rock lithology; The identification model calculates the expected shear strength according to the internal friction angle and cohesion in the first soil mass parameter, and calculates the expected shear modulus according to the elastic modulus and Poisson's ratio in the first soil mass parameter; When the expected shear strength falls within the shear strength range, and the expected shear modulus falls within the shear modulus range, the identification model output is true.

7. A foundation pit soil mechanical parameter back analysis system, characterized in that: include: An acquisition unit is configured to acquire geological survey data of a target foundation pit area, and perform stratigraphic stratification on the target foundation pit area according to the geological survey data to form stratigraphic stratification data; A test unit is configured to sample each stratum in the target foundation pit area according to the stratum stratification data and conduct tests to obtain soil parameters of different strata; A modeling unit is configured to establish a finite element model according to the stratum layering data and the soil parameters, and to regard the excavation and support process of each stratum in the stratum layering data as a working condition; The computing unit is configured as: When excavating the target foundation pit area, actual monitoring data of the target foundation pit area is obtained when excavation and support of one working condition are completed, and simulation calculation of the working condition is performed through the finite element model to obtain simulation monitoring data; Calculating the similarity between the simulated monitoring data and the actual monitoring data as similarity data, and adjusting the soil parameters of the stratum corresponding to the current working condition in the finite element model and recalculating to obtain new simulated monitoring data; Calculating new similarity data according to the new simulation monitoring data and the actual monitoring data, and repeatedly adjusting the soil parameters for simulation calculation until the similarity data is less than a preset value, and using the corresponding soil parameters as the soil parameters of the stratum corresponding to the current working condition; The foundation pit excavation, finite element simulation calculation and soil parameter adjustment are repeated until the foundation pit excavation of the target foundation pit area is completed, and the soil parameters of all strata that have been finally adjusted are used as stratum data of the target foundation pit area.

8. The foundation pit soil mechanical parameter back analysis system according to claim 7 is characterized in that: The acquisition unit is further configured to: Obtaining the buried depth of the stratum boundary from the geological survey data; The target foundation pit area is stratigraphically layered according to the burial depth.

9. The foundation pit soil mechanical parameter back analysis system according to claim 8, characterized in that: The computing unit is further configured to: The simulation monitoring data is vectorized to form a first vector, and the actual monitoring data is vectorized to form a second vector; the elements in the first vector and the second vector both include the ground surface vertical displacement value, the deep displacement value of the support structure and the internal force value of the support structure; A cosine distance between the first vector and the second vector is calculated, and the cosine distance is used as the similarity data.

10. A foundation pit soil mechanical parameter back analysis system according to claim 9, characterized in that: The computing unit is further configured to: Inputting the soil mass parameter into a preset generation model, and receiving a first soil mass parameter output by the generation model; The first soil mass parameter is input into a preset recognition model, and when an output result of the recognition model is true, the first soil mass parameter is used as the adjusted soil mass parameter.

Citation Information

Patent Citations

  • Intelligent early warning and monitoring method for construction of deep foundation pit adjacent to subway based on BP neural network and numerical analysis

    CN117634304A

Cited By

  • Foundation pit deformation prediction method and system, intelligent terminal and storage medium

    CN120124136A

  • Rolling flattening method for foundation caisson construction

    CN121345105A

  • A method for roller compaction of a foundation caisson

    CN121345105B

  • Foundation pit monitoring analysis and geotechnical parameter inversion method and system

    CN122508931A

  • Methods and systems for monitoring and analyzing foundation pits and inverting geotechnical parameters

    CN122508931B