Foundation pit simulation analysis method, system, device and medium based on finite element method

Abstract

The application relates to the technical field of civil engineering, and discloses a foundation pit simulation analysis method based on a finite element method, which comprises the following steps: S1, collecting foundation pit engineering data and environmental information: using geological exploration equipment, environmental monitoring sensors, climate monitoring equipment, underground water level sensors and settlement monitoring sensors to collect and store real-time monitoring data of the geological conditions, soil mechanical properties, underground water level, climate change and settlement of the foundation pit engineering; S2, establishing a multi-physical field coupling model of the foundation pit: according to the foundation pit engineering data collected in step S1, a foundation pit simulation analysis system based on the finite element method, a foundation pit simulation analysis equipment based on the finite element method and a computer readable storage medium are further provided. Through the combination of the finite element method, the multi-physical field coupling model and deep learning optimization, the application realizes efficient and accurate foundation pit stability analysis, automatically generates optimization suggestions, and significantly improves the calculation efficiency, accuracy and real-time dynamic adjustment capability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of civil engineering, in particular to a foundation pit simulation analysis method, system, device and medium based on finite element method. BACKGROUND

[0002] In modern urban construction, foundation pit excavation is an important part of many underground projects such as subways, underground parking lots, underground pipelines, etc. The stability of the foundation pit is directly related to the safety of construction and engineering quality, therefore, accurate assessment of the stability of the foundation pit becomes an indispensable part in the construction process.

[0003] Currently, the stability of the foundation pit is usually analyzed by numerical simulation using finite element method, with the help of professional finite element analysis software, which can accurately simulate the stress, displacement, settlement and other physical phenomena of the soil. The finite element analysis method in the prior art, especially in commercial analysis software such as ANSYS and ABAQUS, has been widely used in foundation pit design and construction. These software can provide effective tool support for engineers by establishing detailed mathematical models to analyze the soil mechanical behavior and structural stability under complex geological conditions, greatly improving the safety and accuracy of civil engineering projects. Especially under relatively simple geological conditions, these software can better predict the stability of the foundation pit and provide feasible technical guidance for construction.

[0004] However, the existing finite element analysis software still has some shortcomings in practical application; first of all, these software usually need high-performance computers for long-time operation, which consumes a lot of computing resources and cannot meet the real-time requirements of project demands; secondly, although the finite element method can handle complex geological conditions, it often relies on simplified models or assumptions in the context of multi-physical field coupling, which affects the accuracy and reliability of the simulation results; in addition, the existing finite element analysis tools are complex to operate and have high technical threshold, ordinary engineers are difficult to operate skillfully without in-depth learning, which leads to the difficulty of practical application; furthermore, the existing technology relies on static data for analysis, lacks the ability to provide real-time feedback and optimization for dynamic changes in the construction process, and cannot adapt to changes in field conditions in time. SUMMARY

[0005] In view of the shortcomings of the prior art, the present application provides a foundation pit simulation analysis method, system, device and medium based on finite element method, which solves the problems of waste of computing resources, high technical threshold, lack of multi-physical field coupling and real-time dynamic optimization in the prior art.

[0006] To achieve the above purpose, the present application realizes the following technical scheme: a foundation pit simulation analysis method based on finite element method, comprising the following steps:

[0007] S1, collect foundation pit engineering data and environmental information: use geological exploration equipment, environmental monitoring sensors, climate monitoring equipment, groundwater level sensors and settlement monitoring sensors to collect and store real-time monitoring data of the geological conditions, soil mechanical properties, groundwater level, climate change and settlement of the foundation pit engineering;

[0008] S2, establish a multi-physical field coupling model of the foundation pit: according to the foundation pit engineering data collected in step S1, a multi-physical field coupling model of the foundation pit is constructed, which includes the interaction of soil mechanics, groundwater flow and heat conduction, forming a coupling equation set for foundation pit stability analysis;

[0009] S3, finite element analysis based on the multi-physical field coupling model: based on the multi-physical field coupling model constructed in step S2, the mechanical behavior, groundwater flow and thermal effect of the foundation pit are simulated using the finite element method, and the stress, displacement and settlement analysis results are obtained;

[0010] S4, nonlinear finite element analysis and adaptive mesh optimization: according to the finite element analysis results in step S3, further adopt nonlinear constitutive model to accurately model the soil, and use error estimation method to optimize the mesh adaptively;

[0011] S5, optimize simulation model parameters and perform deep learning optimization: based on the finite element analysis results in step S4, use convolutional neural network to learn historical data and real-time monitoring data, automatically optimize the parameter settings of the simulation model to enhance the simulation accuracy;

[0012] S6, cloud computing parallel computing optimization: based on the optimized model obtained in step S5, perform parallel computing through a cloud computing platform, distribute simulation tasks to multiple computing nodes to ensure efficient processing of large-scale computing tasks;

[0013] S7, output foundation pit safety evaluation report and provide optimization suggestions: according to the simulation results obtained in step S6, generate a foundation pit safety evaluation report, and provide optimization suggestions based on the safety evaluation results.

[0014] The present application provides a foundation pit simulation analysis method, system, device and medium based on finite element method. It has the following beneficial effects:

[0015] 1, the present application uses cloud computing platform and parallel computing technology to ensure efficient distribution of foundation pit simulation tasks among multiple computing nodes. Unlike traditional single node computing, the system dynamically adjusts resource allocation, improving computing speed and accuracy. This not only speeds up the process of large-scale computing, but also effectively solves the resource waste and computing bottleneck problems in the prior art.

[0016] 2、By combining the finite element method with the multi-physical field coupling model, the present application can comprehensively consider multiple factors such as stress, displacement, groundwater flow and thermal effect, and provide more accurate foundation pit stability analysis. Compared with the scheme of traditional technology which only focuses on a single factor, the present application solves the problem of being unable to accurately evaluate the risk of foundation pit in complex construction environment, and ensures a more reliable construction scheme.

[0017] 3、By combining real-time monitoring data with simulation results, the system can dynamically adjust the analysis model and optimize the scheme. Unlike existing technologies which rely on static data, the present application can reflect various changes in foundation pit construction in real time, improving the ability to respond to unexpected situations. This innovative method effectively reduces risks and optimizes the construction decision-making process. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a method flowchart of the present application;

[0019] Figure 2 is a system structure diagram of the present application;

[0020] Figure 3 is a module architecture diagram of the equipment of the present application;

[0021] Figure 4 is a schematic diagram of the storage medium of the present application. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the specification of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0023] Please refer to the drawings in the specification of the present application Figure 1 The embodiment of the present application provides a foundation pit simulation analysis method based on the finite element method, which includes the following steps: S1, collecting foundation pit engineering data and environmental information: using geological exploration equipment, environmental monitoring sensors, climate monitoring equipment, underground water level sensors and settlement monitoring sensors to collect and store real-time monitoring data of the geological conditions, soil mechanical properties, underground water level, climate change and settlement of the foundation pit engineering;

[0024] S1 Through accurate real-time data acquisition, not only can provide the necessary input for subsequent simulation analysis, but also can help real-time monitoring of the environmental changes of the foundation pit, to ensure that the analysis model conforms to the actual situation. The implementation of step S1 provides data support for the successful implementation of subsequent steps such as multi-physical field coupling analysis, nonlinear finite element analysis and deep learning optimization.

[0025] Firstly, the present embodiment collects real-time data of the foundation pit engineering through various geological exploration equipment, environmental monitoring sensors, climate monitoring equipment, underground water level sensors, and settlement monitoring sensors, etc. The data collected by the sensors and equipment will be stored and processed in real time, including but not limited to soil mechanical properties (such as elastic modulus, friction angle, etc.), underground water level, temperature change, settlement, etc. These data serve as the basis for subsequent model construction and simulation analysis.

[0026] The data collection is carried out through the following types of sensors and equipment:

[0027] Geological exploration equipment: These devices are used to detect the distribution of the soil layers of the foundation pit, the physical properties of each soil layer (such as shear strength, friction angle, elastic modulus, etc.), and underground rock information. Commonly used geological exploration tools include drilling equipment, reflection wave measurement equipment, etc. Through detailed exploration of the geological environment of the foundation pit, the mechanical properties of the foundation pit bottom soil and side wall can be obtained, providing physical parameter support for subsequent analysis.

[0028] Environmental monitoring sensors: These sensors are mainly used to monitor the climate changes of the foundation pit construction environment in real time. By collecting environmental data, potential threats to the safety of the foundation pit due to weather changes can be predicted.

[0029] Underground water level sensors: Changes in underground water level have a significant impact on the stability of the foundation pit, especially during excavation, changes in underground water level can cause soil to slide or lose stability. Therefore, installing underground water level sensors can monitor changes in underground water level in real time and adjust the construction plan in a timely manner. The data collected by the sensors will be transmitted to the system to help determine the flow trend of the underground water around the foundation pit.

[0030] Settlement monitoring sensors: Installed on the foundation pit and surrounding buildings, real-time monitoring of the settlement of the foundation pit. Through the collection of settlement data, settlement problems of the foundation pit or surrounding buildings can be detected early. The data of the settlement monitoring sensors will be used to correct the settlement amount in the simulation model and provide support for subsequent analysis of the stability of the foundation pit.

[0031] The collected data will be processed by a central processing unit to ensure the accuracy and effectiveness of the data. The data processing process includes:

[0032] Data cleaning and preprocessing: The real-time transmitted data may contain outliers and noise, the system will perform preliminary cleaning and preprocessing of the data, including removing noise data, filling missing data, and removing invalid data, etc.

[0033] Data normalization: In order to make the data from different sources consistent, all the data collected by the sensors will be normalized. This step can ensure that the values of different measurement units can be unified in the same dimension, providing consistent data sources for subsequent analysis.

[0034] Data storage and management: Cleaned and processed data will be stored in a database, employing a combination of relational and non-relational databases. Specifically, structured data (such as specific values ​​collected by sensors) will be stored in a relational database, while unstructured data (such as images and reports) will be stored in a non-relational database. This ensures efficient data access and long-term stable storage.

[0035] Data synchronization and real-time monitoring: In some embodiments, to improve the timeliness and reliability of data transmission, the system transmits data to the cloud for synchronous processing and analysis, enabling real-time acquisition of information on the construction environment and the state of the foundation pit. This data synchronization technology ensures the timeliness of monitoring data and simulation analysis results, guaranteeing real-time safety early warnings and decision support for foundation pit construction.

[0036] The physical parameters and formulas involved in data collection will be used in subsequent steps for modeling and analysis. To ensure the accuracy of the data and the establishment of the subsequent simulation model, the definitions of the key parameters and their calculation formulas are as follows.

[0037] Soil elastic modulus (E): The elastic modulus describes the elastic deformation capacity of soil under stress. In this step, the soil elastic modulus (E) is one of the key parameters obtained through geological exploration equipment, and the formula is as follows:

[0038]

[0039] Where: E is the elastic modulus of the soil (unit: Pa); σ is the stress of the soil (unit: Pa); ∈ is the strain of the soil (unit: dimensionless).

[0040] This formula describes the deformation characteristics of soil in the elastic stage. Understanding the elastic modulus can help analyze the deformation and stress response of soil during foundation pit excavation.

[0041] Groundwater flow simulation (Darcy's Law): The simulation of groundwater flow is an indispensable part of foundation pit safety assessment. The basic formula for groundwater flow is Darcy's Law:

[0042]

[0043] Where: q is the water flow rate (unit: m³ / s) 3 / s); K is the soil permeability coefficient (unit: m / s); A is the flow cross-sectional area (unit: m). 2 ); Δh is the head difference (unit: m); L is the length of the water flow path (unit: m).

[0044] The groundwater flow formula can help the system accurately predict the impact of groundwater on the stability of the foundation pit, especially the fluctuation of groundwater level during excavation.

[0045] Settlement (δ): The calculation of settlement is a necessary part to consider in the safety assessment of foundation pit. The formula for calculating the settlement (δ) is as follows:

[0046]

[0047] Where: δ is the settlement (unit: m); P is the applied load (unit: N); L1 is the length of the load (unit: m); A1 is the force area (unit: m 2 ); E is the elastic modulus of the soil (unit: Pa).

[0048] This formula is particularly important for settlement monitoring during the construction phase, as it can help to determine the settlement of the foundation pit and surrounding structures in real time.

[0049] In some embodiments, the technology of wireless sensor network (WSN) will further improve the flexibility and range of data collection. By deploying multiple wireless sensor nodes in the foundation pit area, real-time data transmission can be achieved, and network protocols can be used to ensure stable data transmission. The deployment range of sensors can be expanded to the surrounding area, providing comprehensive monitoring of the entire construction environment.

[0050] In addition, to better realize real-time processing and analysis of data, the use of cloud computing platforms can ensure fast uploading, storage, and analysis of data. After the data stream is transmitted from the field sensors to the cloud platform, centralized processing can be performed through the cloud computing platform, which not only improves the efficiency of data analysis, but also ensures the security and reliability of the data.

[0051] By accurately collecting environmental data, soil characteristics, groundwater changes, and other information of the foundation pit, a solid foundation is provided for subsequent modeling, analysis, and optimization.

[0052] S2, establishing a multi-physical field coupling model of the foundation pit: based on the foundation pit engineering data collected in step S1, a multi-physical field coupling model of the foundation pit is constructed, which includes the interaction of soil mechanics, groundwater flow, and heat conduction, forming a coupled equation set for foundation pit stability analysis;

[0053] In step S2, the goal is to integrate these collected multi-dimensional data into a multi-physical field coupling model to comprehensively describe the mechanical behavior of the foundation pit, groundwater flow, thermal effects, and their interactions. This multi-physical field model not only accurately simulates the behavior of the foundation pit at each stage of the construction process, but also improves the accuracy and real-time performance of the model through effective coupling methods.

[0054] In this embodiment, a multi-physics coupling model is established, which includes soil mechanics, groundwater flow, and heat conduction, and considers their interactions. Each physical field has its specific mathematical model, which is linked through coupling equations to describe their dynamic responses during actual construction.

[0055] Soil mechanics model: To describe the mechanical behavior of soil under different loads and environmental conditions, a nonlinear constitutive model such as the Mohr-Coulomb model or the Hardening-Soil model is used. These models can accurately simulate the elastic and plastic deformation of soil, as well as its yield, hardening, and failure characteristics. By establishing these models, the deformation, stress distribution, and possible failure modes of the soil during excavation can be predicted.

[0056] Groundwater flow model: Groundwater has a significant impact on the foundation pit, especially during excavation, where changes in groundwater level can alter the mechanical properties of the soil. Groundwater flow is typically described by Darcy's law, which states that the water head difference drives groundwater flow. By establishing a groundwater flow model around the foundation pit, the effects of water level changes and water flow on the stability of the foundation pit can be simulated.

[0057] Heat conduction model: Although the thermal effect on the mechanical properties of soil is usually small, in special cases (such as extreme weather or significant changes in groundwater temperature), the thermal effect can significantly change the physical properties of the soil. Therefore, this model includes the effects of temperature changes in the analysis to ensure the comprehensiveness of the foundation pit stability analysis.

[0058] These physical field models are linked through coupling equations to form a complete simulation framework.

[0059] To combine soil mechanics, groundwater flow, and heat conduction, this embodiment uses the Lagrange multiplier method to constrain the interactions between different physical fields. The Lagrange multiplier method introduces an additional constraint variable to couple the physical fields together, allowing the equations of these physical fields to be solved simultaneously in a unified framework.

[0060] In general, the coupling equations will include the following types of equations:

[0061] Soil mechanics equations: Soil mechanics describes the deformation and stress response of soil within the foundation pit under external loads. Soil mechanics equations typically use kinematic equations similar to the classical Galerkin method, which take the form:

[0062]

[0063] where: M effis the effective mass matrix (unit: kg) representing the mass distribution of the soil under dynamic loading; ü is the displacement acceleration (unit: m / s 2 ), describing the acceleration of the soil under external loading; C is the damping matrix (unit: N·s / m) representing the internal friction and energy dissipation characteristics of the soil; is the displacement velocity (unit: m / s) describing the velocity of the soil under loading; K eff is the effective stiffness matrix (unit: N / m) representing the elastic response of the soil. u is the displacement vector (unit: m) representing the displacement of the soil at different time steps; F ext is the external load (unit: N), such as the weight of the building, construction equipment load, etc.; F int is the internal reaction force (unit: N) describing the distribution of internal forces in the soil.

[0064] Groundwater flow equation: The groundwater flow equation is based on Darcy's law, which describes the basic law of groundwater flow in the soil. It uses the "Darcy's law" disclosed in S1.

[0065] This equation can simulate the flow of water in the foundation pit area, especially the influence of groundwater on the stability of the foundation pit during excavation.

[0066] Heat conduction equation: The heat conduction of the soil will cause the temperature change of the soil during excavation, which will affect the physical properties of the soil. The heat conduction equation is:

[0067]

[0068] where: T is the temperature field (unit: °C or K) describing the temperature distribution of the soil; t is the time (unit: s) representing the process of heat conduction changing with time; k1 is the thermal conductivity (unit: W / (m·K)) describing the ability of the soil to conduct heat; is the temperature gradient (unit: K / m) describing the rate of change of temperature in space.

[0069] This equation is used to simulate the propagation of temperature in the soil, considering the potential impact of temperature on the stability of the soil.

[0070] Due to the complexity of the coupling between soil mechanics, groundwater flow and heat conduction, it may be very difficult to directly solve these coupled equation sets. Therefore, the finite element method (FEM) is used in this embodiment to numerically solve these equations. In the finite element method, the entire foundation pit area is discretized into a finite number of small elements, and by solving the equations of each small element, the final results of stress, displacement, settlement, temperature and water flow of the entire foundation pit are obtained.

[0071] To improve computational efficiency and ensure the accuracy of the results, this embodiment employs an adaptive mesh optimization technique. Based on error evaluation during the simulation process, the mesh in areas with large stress changes is automatically refined, while the mesh in other areas is coarsened, thereby reducing the computational load and improving the accuracy of the calculations.

[0072] In certain embodiments, to further enhance the adaptability of the model, a heterogeneous permeability model can also be introduced to consider the differences in permeability characteristics of different regions of the soil. Specifically, in different regions of the soil, the permeability coefficient K may have significant differences, which have important effects on groundwater flow. Therefore, considering the heterogeneous permeability of different regions of the soil in modeling will improve the simulation accuracy of groundwater flow.

[0073] In addition, it is also possible to consider introducing a dynamic heat source model into the heat conduction equation. Especially in extreme weather conditions, the temperature change of the soil may affect the stability of the foundation pit. By dynamically adjusting the parameters of the heat source model, the accuracy of the heat conduction analysis can be further improved.

[0074] By using the Lagrange multiplier method to constrain the interaction between these physical fields, the integrity and consistency of the coupled equations are ensured.

[0075] S3, finite element analysis based on multi-physical field coupling model: based on the multi-physical field coupling model constructed in step S2, the mechanical behavior of the foundation pit, groundwater flow and thermal effects are simulated using the finite element method, and the stress, displacement and settlement analysis results are obtained;

[0076] The core task of S3 is to use the finite element method to perform detailed simulation analysis based on these coupled models, so as to accurately calculate the influence of the mechanical behavior of the foundation pit, groundwater flow and thermal effects on the stability of the foundation pit. The ultimate goal of this step is to obtain the key parameters such as stress, displacement and settlement of the foundation pit, and to evaluate the stability of the foundation pit.

[0077] Firstly, by discretizing the foundation pit area into finite elements and solving the mechanical behavior of the foundation pit, groundwater flow and thermal effects within these elements, the finite element method can effectively handle complex geometric shapes, material nonlinearity and boundary conditions, etc.

[0078] Finite element method (FEM) as a numerical calculation method, can convert complex continuum problems into discrete numerical problems, and has been widely used in the fields of structural mechanics, fluid mechanics and heat conduction. In the simulation analysis of foundation pit, the implementation steps of finite element method include:

[0079] Discretization: In finite element analysis, the excavation area first needs to be discretized into a number of small elements. The shape of these small elements is usually triangular or quadrilateral (for two-dimensional problems), or tetrahedral or hexahedral (for three-dimensional problems). Within each small element, calculations of physical quantities such as stress, displacement, temperature, etc. are performed. Through this discretization method, the entire area of the excavation is converted into a grid composed of multiple elements.

[0080] Boundary conditions and loading conditions: In order to simulate the behavior of the excavation in a real environment, the boundary conditions and loading conditions of the model must be accurately set. Boundary conditions usually include support around the excavation, constraints on the excavation face, etc. Loading conditions include self-weight, construction load in the excavation, and changes in external environment, etc.

[0081] In some embodiments, the loading conditions may be dynamic loads, i.e., loads that change over time. For example, during the excavation process, the construction equipment load and the self-weight of the upper layer of soil may change as the construction progresses, and the application of dynamic load models can better reflect this change.

[0082] Solving finite element equations: The finite element analysis of the excavation is based on the following basic equations for numerical solution:

[0083] [K]·{u}={F ext +F fluid};

[0084] Where: [K] is the stiffness matrix (unit: N / m), representing the system's response to external loads; {u} is the displacement vector (unit: m), describing the displacement of each node in the excavation; {F ext} is the external load (unit: N); {F fluid} is the additional force caused by water flow (unit: N), which is the force generated by the water pressure caused by groundwater flow.

[0085] Coupled equation solution: In step S2, it has been introduced how to consider the interaction between soil mechanics, groundwater flow and heat conduction through coupled equations. In the finite element method solution, the coupling effect of each physical field in the solution process is solved through the related matrix equation.

[0086] In the process of excavation analysis, the interaction between multiple physical fields such as soil mechanics, groundwater flow and heat conduction cannot be ignored. Therefore, in the simulation process of the finite element method, the coupling effect between these physical fields must be considered simultaneously.

[0087] Coupling of soil mechanics and groundwater flow: Groundwater flow can generate water pressure on the soil, thereby affecting the deformation and stress distribution of the soil. This coupling can be described by the following formula:

[0088] F fluid = ∫ A Δh·K·ndA;

[0089] where: F fluid is the additional force caused by water flow (unit: N), generated by the pore pressure of groundwater flow; Δh is the water head difference (unit: m), the pressure difference between two points of water flow; K is the permeability coefficient of soil (unit: m / s); n is the normal vector (unit: dimensionless), indicating the direction of force action; A is the flow cross-sectional area (unit: m 2 ); dA is the area element (unit: m 2 ).

[0090] Coupling of soil mechanics and heat conduction: The change of temperature of soil will affect its elastic modulus and yield strength, thus changing its mechanical response. The additional force caused by thermal effect can be represented by the following formula:

[0091] F thermal = ∫ A α·ΔT1·n1dA2;

[0092] where: F thermal is the additional force caused by thermal effect (unit: N), the force generated by thermal expansion caused by temperature change; α is the thermal expansion coefficient (unit: 1 / K), describing the thermal expansion characteristics of soil; ΔT1 is the temperature change (unit: ℃ or K), indicating the temperature change of soil during excavation due to thermal effect; n1 is the normal vector (unit: dimensionless), indicating the direction of deformation caused by thermal expansion; A2 is the area (unit: m 2 ), describing the cross-sectional area of thermal expansion action.

[0093] In order to accelerate the finite element solving process, especially in the simulation of large-scale foundation pit engineering, parallel computing technology is adopted. By distributing the calculation task to multiple processing units (such as multi-core CPU or cloud computing platform), multiple sub-problems can be processed simultaneously, significantly improving the calculation efficiency.

[0094] In some embodiments, adaptive mesh optimization is introduced into the calculation process. This technology automatically adjusts the refinement level of the mesh according to the stress changes and physical properties within the foundation pit area. In the stress concentration area, the mesh will be refined, thereby improving the calculation accuracy; in the relatively stable area, the mesh will remain coarse to reduce the amount of calculation.

[0095] In some embodiments, as the construction environment changes, real-time adjustment of the simulation model may be needed. Based on real-time monitoring data (such as groundwater level, settlement, temperature, etc.), relevant parameters in the finite element model can be dynamically updated to ensure the accuracy of the simulation analysis.

[0096] In addition, the introduction of heterogeneous soil layer models can further improve the accuracy of groundwater flow and heat conduction analysis. In practical applications, the physical properties of different soil layers (such as permeability and thermal conductivity) may differ significantly, which has a significant impact on the stability of the foundation pit. Therefore, considering the heterogeneous characteristics of different soil layers is crucial for optimizing the simulation model.

[0097] By optimizing the calculation process, introducing parallel computing technology, and using adaptive mesh optimization methods, the calculation efficiency and accuracy are further improved, providing a scientific basis for the safety evaluation and construction optimization of foundation pit engineering.

[0098] S4, nonlinear finite element analysis and adaptive mesh optimization: based on the results of the finite element analysis in step S3, further precise modeling of the soil is performed using a nonlinear constitutive model, and an error estimation method is used to adaptively optimize the mesh;

[0099] In the foregoing technical solution, the finite element method is used to solve the multi-physical field coupling model of the foundation pit, and the stress, displacement, settlement, and other results of the foundation pit at different construction stages are obtained. However, the behavior of the soil in the foundation pit often exhibits nonlinear characteristics, especially during excavation, when the soil is subjected to large loads, the nonlinear effects that occur can have a significant impact on the stability of the foundation pit. Therefore, in S4, the key task is to model the soil more accurately through nonlinear finite element analysis, while using adaptive mesh optimization methods to ensure higher computational accuracy in key areas and improve overall computational efficiency.

[0100] In this embodiment, a nonlinear constitutive model, particularly the Mohr-Coulomb or Hardening-Soil model, is first used to accurately describe the nonlinear behavior of the soil. Then, based on the aforementioned model and analysis results, an error estimation method is used for adaptive mesh optimization. In this way, the system can dynamically adjust the grid density according to the stress and displacement distribution, thereby ensuring computational accuracy while reducing waste of computational resources.

[0101] To accurately describe the nonlinear behavior of the soil under different loads, this embodiment uses the commonly used Mohr-Coulomb model or Hardening-Soil model. These models can effectively capture the nonlinear characteristics of soil, such as yield, hardening, and softening, especially during the excavation of the foundation pit, where the stress on the soil often exceeds the yield point, causing plastic flow or hardening of the soil. Therefore, using a nonlinear constitutive model helps improve the accuracy of the foundation pit simulation analysis.

[0102] The constitutive relationship of the Mohr-Coulomb model is as follows:

[0103] σ = σ yield +k2·∈;

[0104] where σ is the stress (unit: Pa), representing the total stress in the soil; σ yield is the yield stress (unit: Pa), which is the stress at which the soil begins to deform plastically; k2 is the hardening coefficient (unit: Pa), describing the change in stiffness of the soil during plastic deformation; ∈ is the strain (unit: dimensionless), describing the degree of deformation of the soil.

[0105] This model can effectively simulate the plastic deformation that may occur in the soil during the excavation of the foundation pit by modeling the stress-strain relationship of the soil.

[0106] The solution process in nonlinear finite element analysis usually uses the Newton-Raphson method. Since the stiffness matrix in the nonlinear equation set changes with the displacement, the Newton-Raphson method can solve the nonlinear equation by iteration to gradually obtain the true values of stress and displacement.

[0107] In each iteration, the system updates the displacement by the following formula:

[0108] K(u)·Δu=F-F current ;

[0109] where K(u) is the nonlinear stiffness matrix (unit: N / m), which depends on the current displacement field, representing the system's response to the load; Δu is the displacement increment (unit: m), representing the amount of displacement change in each iteration; F is the external load vector (unit: N), representing the external load applied to the foundation pit; F current is the current load vector (unit: N), representing the load calculated by the current displacement.

[0110] Through iterative solution, until the displacement increment Δu\Delta\mathbf{u}Δu converges, the final displacement, stress distribution, etc. of the foundation pit can be obtained.

[0111] In complex nonlinear analysis, especially in stress concentration areas, the choice of mesh density is crucial. Traditional uniform mesh division may not be able to fully capture the stress changes in these areas, therefore, this embodiment adopts an adaptive mesh optimization method, which dynamically adjusts the mesh resolution according to the calculation results.

[0112] The key steps of adaptive mesh optimization include:

[0113] Error estimation: By evaluating the error of stress, displacement or other physical quantities of each element, it is determined which areas need to be refined in the mesh.

[0114] Mesh refinement and coarsening: Based on the error evaluation results, the mesh is refined in areas with stress concentration, while it is coarsened in smooth areas.

[0115] The formula for error estimation is:

[0116]

[0117] where η is the error estimate (unit: dimensionless), representing the error ratio in a certain calculation area; u error is the error of stress or displacement (unit: m or Pa), the error amount in the calculation result; u total is the total stress or displacement of the calculation result (unit: m or Pa), describing the stress or displacement of the soil.

[0118] This formula helps the system evaluate the calculation accuracy of different areas, thereby determining the refinement and coarsening of the mesh.

[0119] The computational load of nonlinear finite element analysis and adaptive mesh optimization is usually very large, especially in large-scale foundation pit engineering. In order to improve the calculation efficiency, this embodiment adopts parallel computing technology, which distributes the calculation tasks to multiple computing nodes to speed up the calculation process.

[0120] In some embodiments, optimization is performed through a multi-level parallel strategy. Specifically, the calculation task can not only be parallelized at the node level, but also be processed in blocks at the data level, with each computing node responsible for processing a portion of the data. This strategy can effectively improve the calculation efficiency and reduce the overall calculation time.

[0121] In addition to the basic nonlinear analysis and mesh optimization method, further optimization can also be performed under different conditions, and it is crucial to consider the different material properties between soil layers for the accuracy of the model.

[0122] In addition, in order to cope with dynamic loads such as changes in construction equipment loads, the system can combine real-time sensor data to update the load model in real time, making the simulation results more close to the actual construction situation.

[0123] Through the application of nonlinear constitutive models, the complex deformation behavior of soil under load can be accurately described, and through adaptive mesh optimization, the calculation accuracy can be improved while reducing unnecessary consumption of computing resources. In addition, combined with parallel computing technology, the challenge of large-scale computing tasks is effectively solved, ensuring that the safety evaluation of the foundation pit can be efficiently and accurately performed.

[0124] S5, optimize simulation model parameters and perform deep learning optimization: based on the finite element analysis results of step S4, use a convolutional neural network to learn historical data and real-time monitoring data, automatically optimize the parameter settings of the simulation model to enhance simulation accuracy;

[0125] In the aforementioned steps, the stability of the foundation pit has been simulated in detail through nonlinear finite element analysis and adaptive mesh optimization. However, as the model complexity increases, it becomes increasingly difficult to manually adjust the model parameters, and traditional calculation methods may require a large amount of computing resources and time. Therefore, in S5, the introduction of deep learning optimization is proposed to automate parameter adjustment and improve simulation accuracy.

[0126] In this embodiment, based on the finite element analysis results obtained in step S4, a convolutional neural network (CNN) is used to learn historical data and real-time monitoring data. Through training the neural network, the system can automatically optimize the parameter settings in the simulation model, improve the accuracy of simulation analysis, and make the model more efficient in dealing with complex and variable actual situations.

[0127] Deep learning models, especially convolutional neural networks (CNN), perform well in image recognition and complex pattern recognition. For foundation pit simulation analysis, CNN is used to extract features from a large amount of historical case data and real-time monitoring data, and automatically adjust the parameters of the model. This not only reduces manual intervention, but also improves the predictive ability and adaptability of the model.

[0128] In some embodiments, the system optimizes the following model parameters through deep learning training using historical data and real-time data:

[0129] Constitutive model parameters of soil body (such as hardening coefficient, yield stress, etc.);

[0130] Permeability coefficient and water head difference, affecting groundwater flow model;

[0131] Thermal expansion coefficient, affecting heat conduction model;

[0132] Load and boundary conditions to simulate changes in environment and external conditions during construction.

[0133] Through the optimization of the deep learning model, these parameters can be automatically adjusted to ensure that the simulation model has more accurate calculation results at each stage, thereby providing a scientific basis for engineering decision-making at different construction stages.

[0134] By using a convolutional neural network (CNN), this network structure is particularly suitable for processing input data with spatial structure, such as images, sensor data, etc. CNN can extract feature information in data layer by layer through multiple convolutional layers, pooling layers and fully connected layers. In foundation pit simulation, CNN can learn the relationship between soil body mechanics response, groundwater flow and thermal effect from historical case data, and optimize the model based on real-time monitoring data.

[0135] Input data: Historical data includes construction plans, soil distribution, environmental monitoring data (such as climate, groundwater level, etc.), and corresponding construction results (such as settlement, stress, etc.). Real-time monitoring data includes real-time collected stress, displacement, temperature, etc. information during construction.

[0136] Feature extraction and learning: CNN automatically extracts spatial features in input data through multiple convolutional layers, such as stress distribution of soil, flow state of groundwater, etc. After pooling operation, the network can gradually compress data and retain important feature information.

[0137] Parameter optimization: Through the backpropagation algorithm, the network adjusts the weights according to the error in the training data to optimize the parameters in the model. Finally, the trained model can automatically adjust the parameter settings in the simulation model according to new input data (such as construction progress and environmental changes).

[0138] The backpropagation algorithm is a common optimization algorithm in deep learning, and its basic process is as follows:

[0139]

[0140] where: w new is the optimized network weight; w old is the current network weight; η is the learning rate (unit: dimensionless), which controls the step size of each weight update; is the gradient of the loss function (unit: dimensionless), which represents the contribution of the current weight to the error.

[0141] Through the backpropagation algorithm, CNN can gradually adjust its parameters so that the simulation results are more consistent with the actual situation and improve the prediction accuracy.

[0142] During the training process, the system continuously optimizes model parameters through real-time feedback monitoring data (such as settlement, groundwater level changes, climate changes, etc.). This adaptive optimization process can automatically adjust the nonlinear parameters of the model to ensure that the model maintains high accuracy when facing different construction conditions. Through this way, the system can update and adapt to any changes in the foundation pit construction process in real time, avoiding the tedious process of manual parameter adjustment.

[0143] In some embodiments, the deep learning model not only automatically adjusts the physical model parameters, but also verifies and optimizes the simulation results under different construction scenarios. For example:

[0144] Groundwater flow model: Optimize parameters such as water head difference and permeability coefficient through deep learning model to better simulate the flow changes of groundwater.

[0145] Soil constitutive model: Automatically adjust parameters such as hardening coefficient and yield stress to ensure accurate description of the nonlinear behavior of soil.

[0146] Thermal effect model: automatically adjust the thermal expansion coefficient and the influence of temperature change on soil according to real-time climate data and groundwater level changes.

[0147] In practical applications, this embodiment can also introduce deep reinforcement learning, so that the model can continuously adjust and optimize itself according to the real-time changing environmental conditions during construction.

[0148] In addition, as the complexity of foundation pit engineering increases, the training data of the deep learning model can be continuously expanded and updated. By continuously absorbing new engineering cases and monitoring data, the deep learning model can continuously optimize during construction, improving the accuracy of its foundation pit stability assessment.

[0149] Through the learning and optimization of historical data and real-time monitoring data by convolutional neural network (CNN), the simulation model can be adjusted in real time during construction, ensuring the accuracy and reliability of foundation pit safety assessment.

[0150] S6, cloud computing parallel computing optimization: based on the optimized model obtained in step S5, parallel computing is performed through a cloud computing platform to distribute simulation tasks to multiple computing nodes, ensuring efficient processing of large-scale computing tasks; in the foregoing steps, the parameters of the simulation model are optimized based on deep learning, enabling the foundation pit simulation analysis to automatically adjust and improve simulation accuracy under different environmental conditions. However, due to the scale and complexity of foundation pit engineering, especially in large-scale foundation pit analysis, the computing power of a single computer may not be able to meet the real-time analysis and efficient simulation computing requirements. Therefore, S6 introduces cloud computing platform and parallel computing technology to solve this problem. By distributing computing tasks to multiple computing nodes, cloud computing parallel computing can significantly speed up the simulation process, improve analysis efficiency, and reduce hardware resource consumption.

[0151] To further improve computing efficiency, the foundation pit simulation task is divided into multiple sub-tasks and executed simultaneously through the distributed computing power of the cloud computing platform. In addition, the cloud computing platform can dynamically allocate computing resources to ensure smooth operation of computing tasks under different load conditions.

[0152] In the cloud computing platform, dynamic scheduling of elastic computing resources is the key to improving computing efficiency and reducing resource waste. According to different computing requirements and task loads, the cloud platform will adjust computing resources in real time. For parallel computing tasks, the optimization of task allocation is crucial to improve overall computing efficiency.

[0153] The formula for elastic computing resource scheduling and load balancing is as follows:

[0154]

[0155] where: R task is the computational resource allocated to each task (unit: dimensionless). According to the complexity and computational demand of the task, the computational capacity that each sub-task can obtain is determined; R available is the total available computational resource (unit: dimensionless). It represents the total amount of computational capacity available for use by the cloud platform at the current time, including processors, memory, storage, etc.; N is the number of computing nodes (unit: dimensionless). It represents the number of computing nodes used by the cloud computing platform during parallel computing.

[0156] This formula describes the reasonable allocation of computational resources. By evenly distributing the total available computational resources among the number of tasks, each task can obtain appropriate computational resources, thereby accelerating the overall simulation analysis process.

[0157] During parallel computing, computational tasks are decomposed into multiple sub-tasks and processed in parallel through multiple computing nodes. These sub-tasks can be stress analysis of different regions, calculation of different time steps, etc. Through reasonable sub-task allocation, the system can significantly improve the speed and efficiency of simulation computation.

[0158] The task allocation formula is as follows:

[0159]

[0160] where: T i is the sub-task allocated to the i-th node (unit: dimensionless); T total is the total computational task amount (unit: dimensionless); M i is the node weight (unit: dimensionless).

[0161] This formula ensures that each computing node matches its computational capacity with the amount of tasks allocated to it, thereby optimizing load balancing and computational efficiency during computation.

[0162] In data-level parallel computing, model data is chunked, and each computing node is responsible for processing part of the data block. Through parallel computing, multiple computing nodes simultaneously process different data blocks, improving overall computational efficiency.

[0163] The data chunking and processing formula is as follows:

[0164]

[0165] where: D i is the data block processed by the i-th computing node (unit: dimensionless); D total is the total data amount (unit: dimensionless); P i is the node processing capacity (unit: dimensionless).

[0166] This formula represents the reasonable allocation of total data volume according to the processing capacity of each node, ensuring that each node will not be overloaded when processing data, thus optimizing the parallel computing process.

[0167] To ensure load balancing of each node in the parallel computing process, the cloud computing platform dynamically adjusts task allocation to ensure that the load of each node is as equal as possible, thus avoiding some nodes being overloaded and affecting the overall computing efficiency.

[0168] The load balancing calculation formula is as follows:

[0169]

[0170] Where: L i is the load of the i-th node (unit: dimensionless); T i is the amount of tasks allocated to the i-th node (unit: dimensionless); C i is the computing capacity of the i-th node (unit: dimensionless).

[0171] This formula is used to calculate the load of each node to ensure that task allocation avoids overloading or underloading of some nodes, thus improving computing efficiency.

[0172] To cope with dynamic changes in computing load, the cloud computing platform dynamically adjusts computing resources according to real-time computing needs to ensure that the computing capacity of the system always matches the needs of computing tasks.

[0173] The dynamic resource scheduling formula is as follows:

[0174] R assigned = R available · F demand ;

[0175] Where: R assigned is the computing resources allocated to the current task (unit: dimensionless); R available is the currently available computing resources (unit: dimensionless); F demand is the demand factor of the current computing task (unit: dimensionless).

[0176] Through this formula, the cloud platform can dynamically allocate resources according to the needs of computing tasks to ensure that resource allocation in the computing process will not be bottlenecked by fluctuations in computing load.

[0177] The parallel computing and load balancing strategy of this embodiment can be combined with real-time monitoring data to further optimize the resource scheduling and task allocation of the cloud computing platform.

[0178] In addition, as the scale of computing tasks increases, multi-level parallel computing and deep learning optimization of cloud computing platforms can be combined. Through real-time feedback adjustment of the parameters and computing strategies of the simulation model by the deep learning model, the efficiency and accuracy of simulation analysis are further improved.

[0179] With the support of dynamic allocation of computing resources and load balancing, the system can efficiently and stably handle large-scale foundation pit simulation tasks, ensuring the efficiency and accuracy of engineering calculations. Through real-time monitoring of data feedback, the system can automatically adjust computing resources and simulation models to provide accurate safety assessments and optimization recommendations for foundation pit construction.

[0180] S7, outputting a foundation pit safety assessment report and providing optimization suggestions: based on the simulation results obtained in step S6, a foundation pit safety assessment report is generated, and optimization suggestions are provided according to the safety assessment results;

[0181] In S7, the system will generate a foundation pit safety assessment report based on these simulation results and provide optimization suggestions based on the assessment results to ensure the safety of foundation pit construction.

[0182] The system automatically generates a safety assessment report for the foundation pit. The report content is based on the simulation results and evaluates the stability of the foundation pit in each construction stage in detail. Specifically, the report analyzes the stress distribution, displacement change, settlement, and other key indicators in different construction stages, assesses possible risk points, and proposes countermeasures. In addition, the report will also provide optimization suggestions based on the actual situation of foundation pit construction, combined with historical data and real-time monitoring information.

[0183] In this embodiment, the generation of the foundation pit safety assessment report mainly depends on the following aspects:

[0184] Stress analysis: when evaluating the stability of the foundation pit, the stress in each region of the foundation pit will be analyzed first. By interpreting the stress data in the simulation results, it is evaluated whether the structure of the foundation pit can withstand the load generated during the construction process.

[0185] Displacement and settlement analysis: in addition to stress analysis, displacement and settlement of the foundation pit are important factors affecting stability. During the construction process, deformation of the soil around the foundation pit may cause uneven settlement, which in turn affects the stability of the structure. The report will combine displacement data in the simulation results to evaluate whether the foundation pit has undergone excessive deformation, and analyze the risk of settlement based on the nonlinear behavior of the soil.

[0186] Groundwater flow impact analysis: In some embodiments, the flow of groundwater has a significant impact on the stability of the foundation pit. Changes in groundwater levels can cause changes in the strength and stiffness of the soil, which in turn affects the stability of the foundation pit. Therefore, the foundation pit safety assessment report also includes an analysis of the impact of groundwater flow on the stability of the foundation pit. The system will evaluate the additional forces that water flow may bring and the impact on the foundation structure based on the simulation results of groundwater level changes and flow.

[0187] Thermal effect analysis: For some specific foundation pit construction environments, such as high temperature or low temperature areas, thermal effects can also affect the soil, causing expansion or contraction of the soil, which can lead to instability. The system generates a thermal effect analysis report by simulating the deformation behavior of the soil at different temperatures.

[0188] The foundation pit safety assessment report not only provides analysis results of the current foundation pit state, but also generates optimization suggestions based on the analysis results to help the construction party improve the design or take emergency measures.

[0189] Support system optimization suggestions: In some embodiments, the support system of the foundation pit may need to be further strengthened. The report will make suggestions on increasing the number and arrangement density of support piles based on the results of stress distribution and settlement analysis.

[0190] Soil reinforcement scheme: For some foundation pits with soft or uneven soil, soil reinforcement may be needed. The report will propose soil reinforcement schemes such as grouting, soil nailing, deep mixing, etc. based on the mechanical properties of the soil and the impact of groundwater flow to enhance the stability and bearing capacity of the soil.

[0191] Groundwater level control scheme: For foundation pits that are significantly affected by groundwater flow, the report may propose a groundwater level control scheme. By adjusting the drainage system or strengthening the waterproof measures of the enclosure structure, the adverse effects of groundwater on the foundation pit can be avoided.

[0192] Monitoring and control measures: In addition to soil reinforcement and support system optimization, the report will also make suggestions for real-time monitoring to keep track of the safety status during the construction process of the foundation pit.

[0193] In this embodiment, the generation of the foundation pit safety assessment report relies on the data processing module in the system. First, the system obtains relevant engineering data and construction information from the historical case database and calibrates the simulation results based on real-time monitoring data. Then, the system generates the report through the following steps:

[0194] Data integration and analysis: Compare the simulation results with the actual monitoring data to ensure the accuracy of the simulation results. Based on the data analysis results, the system judges the stability of the foundation pit at different construction stages.

[0195] Risk Assessment: Based on the analysis results, the system automatically identifies possible risk points, such as excessive stress and rapid settlement, and evaluates the potential instability of the foundation pit.

[0196] Optimization Suggestions Generation: After identifying the risks, the system automatically generates targeted optimization suggestions based on historical cases and engineering experience, such as increasing support and adjusting groundwater levels.

[0197] Automatic Report Generation: Finally, the system integrates all analysis results and optimization suggestions into a complete report, including detailed charts and data, as well as corresponding textual descriptions. The report format is standardized, making it easy for users to read and reference.

[0198] S7 generates a foundation pit safety evaluation report based on simulation analysis results and provides optimization suggestions based on real-time data, providing detailed safety evaluation and improvement measures for construction units. The report not only provides current state analysis of the foundation pit, but also proposes effective solutions for potential risks, which helps to ensure the safety and quality of foundation pit construction.

[0199] The foundation pit simulation analysis system based on the finite element method described below can be mutually referred to the foundation pit simulation analysis method based on the finite element method described above.

[0200] Please refer to the attached Figure 2 , the present application also provides a foundation pit simulation analysis system based on the finite element method, comprising:

[0201] Data Acquisition Module: This module uses geological exploration equipment, environmental monitoring sensors, climate monitoring equipment, groundwater level sensors, and settlement monitoring sensors to collect and store real-time data of foundation pit projects;

[0202] Multi-physical field coupling modeling module: based on the collected foundation pit engineering data, a multi-physical field coupling model including soil mechanics, groundwater flow and heat conduction is established;

[0203] Finite Element Analysis Module: Based on the multi-physical field coupling model, the finite element method is used to simulate the mechanical behavior, groundwater flow and thermal effect of the foundation pit;

[0204] Nonlinear analysis and mesh optimization module: use Mohr-Coulomb nonlinear constitutive model for soil nonlinear analysis, and optimize the finite element mesh according to error estimation. This module automatically adjusts the grid density to ensure fine calculation in stress concentration areas, while coarsening the grid in other areas;

[0205] Deep learning optimization module: use convolutional neural network to learn historical data and real-time monitoring data, automatically optimize the parameters of the simulation model;

[0206] Cloud computing and parallel computing module: based on the optimization model, distributed parallel computing is carried out by using the cloud computing platform, which adopts elastic computing resources, dynamically allocates tasks according to the computing load, and uses load balancing technology to ensure that the load of each computing node is uniform, avoiding single-point overload.

[0207] Report generation and optimization suggestion module: generate a foundation pit safety evaluation report according to the simulation results, the report content includes stability analysis of foundation pit, construction risk assessment, and safety assessment of each construction stage.

[0208] The system of the embodiment can be used to execute the above-mentioned method embodiments, and has similar principles and technical effects, which will not be repeated here.

[0209] The finite element method-based foundation pit simulation analysis device described below can be mutually corresponding with the finite element method-based foundation pit simulation analysis method described above.

[0210] Please refer to the accompanying Figure 3 The application also provides a finite element method-based foundation pit simulation analysis device, which comprises:

[0211] Data acquisition device: including geological exploration equipment, environmental monitoring sensors, groundwater level sensors and settlement monitoring sensors; calculation and simulation processing device: using high-performance computer hardware, including processor, memory and hard disk storage, supporting efficient processing of parallel computing tasks;

[0212] Cloud computing platform: a cloud platform providing elastic computing resources, supporting cloud storage and computing;

[0213] Deep learning processing unit: equipped with a deep learning processing unit for training a convolutional neural network and optimizing foundation pit simulation parameters;

[0214] Output and feedback device: including display screen, printing device and network interface, for showing simulation results and generating foundation pit safety evaluation report.

[0215] The device of the embodiment can be used to execute the above-mentioned method embodiments, and has similar principles and technical effects, which will not be repeated here.

[0216] Please refer to the accompanying Figure 4 The application also provides a computer readable storage medium having program code stored thereon, which causes a computer to execute the finite element method-based foundation pit simulation analysis method, and the storage medium comprises:

[0217] Data collection and storage instructions for controlling the data acquisition device to collect and store real-time data of the foundation pit project;

[0218] The multi-physical field coupling model construction instruction is used for constructing a multi-physical field coupling model of the foundation pit according to the collected foundation pit engineering data, and generating a coupling equation set;

[0219] The finite element simulation analysis instruction is used for performing finite element method simulation calculation on the basis of the constructed multi-physical field coupling model to obtain analysis results of stress, displacement and settlement;

[0220] The nonlinear finite element analysis and grid optimization instruction is used for accurately modeling the soil body by using a nonlinear constitutive model and performing adaptive grid optimization according to the finite element simulation results;

[0221] The deep learning optimization instruction is used for learning historical data and real-time monitoring data by using a convolutional neural network, and automatically optimizing parameter settings of a simulation model;

[0222] The cloud computing and parallel computing optimization instruction is used for performing parallel calculation through a cloud computing platform, distributing simulation tasks to multiple computing nodes, and ensuring fast processing of large-scale calculation tasks.

[0223] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for simulation analysis of a foundation pit based on finite element method, characterized in that, Comprise the following steps: S1, collect foundation pit engineering data and environmental information: using geological exploration equipment, environmental monitoring sensors, climate monitoring equipment, groundwater level sensors and settlement monitoring sensors to collect and store real-time monitoring data of geological conditions, soil mechanical properties, groundwater level, climate change and settlement of foundation pit engineering; S2, establish a multi-physical field coupling model of the foundation pit: according to the foundation pit engineering data collected in step S1, a multi-physical field coupling model of the foundation pit is constructed, which includes the coupling equations of soil mechanics and groundwater flow; Coupling equations of soil mechanics and heat conduction; Based on the solving method of Lagrange multiplier method, the dynamic coupling between mechanics, fluid and heat conduction is ensured, the interaction of soil mechanics, groundwater flow and heat conduction is formed, and the coupling equation set is used for foundation pit stability analysis; S3, finite element analysis based on multi-physical field coupling model: based on the multi-physical field coupling model constructed in step S2, the mechanical behavior, groundwater flow and thermal effect of the foundation pit are simulated using finite element method, and the stress, displacement and settlement analysis results are obtained; S4, nonlinear finite element analysis and adaptive mesh optimization: according to the finite element analysis results in step S3, the soil is further modeled using nonlinear constitutive model, and the mesh is adaptively optimized using error estimation method, including: using nonlinear constitutive model to describe the nonlinear behavior of soil, and analyzing the relationship between foundation pit load and deformation; Based on the error estimation method, the mesh is refined in the deformation intensive area and coarsened in other areas; Dynamic mesh refinement and coarsening adjust the mesh resolution by automatically detecting stress change and geological characteristics to improve calculation accuracy and efficiency; S5, optimize simulation model parameters and perform deep learning optimization: based on the finite element analysis results in step S4, use convolutional neural network to learn historical data and real-time monitoring data, and automatically optimize the parameter settings of simulation model to enhance simulation accuracy; Deep learning optimization simulation model includes: using convolutional neural network model to extract features of foundation pit soil data, groundwater level, climate change input data, and automatically optimizing simulation parameters through training process; Adjust the weights in the convolutional neural network model through back propagation algorithm to reduce the error of simulation results, and automatically adjust the model parameters according to real-time data; S6, cloud computing parallel computing optimization: based on the optimized model obtained in step S5, parallel computing is performed through cloud computing platform, and simulation tasks are distributed to multiple computing nodes to ensure efficient processing of large-scale computing tasks; S7, output foundation pit safety evaluation report and provide optimization suggestions: according to the simulation results obtained in step S6, generate foundation pit safety evaluation report, and provide optimization suggestions according to safety evaluation results.

2. The finite element method-based simulation analysis method for a foundation pit according to claim 1, characterized in that, The cloud computing and parallel computing optimization includes: Divide the foundation pit simulation analysis task into multiple subtasks, and perform distributed computing through cloud computing platform to speed up the calculation; Use elastic computing resources to dynamically allocate computing tasks according to the computing load to improve the computing efficiency; Load balancing technology is used to ensure uniform load distribution among all computing nodes and avoid single-point overload.

3. The finite element method-based simulation analysis method of a foundation pit according to claim 1, characterized in that, The foundation pit safety assessment report includes: Based on the simulation results, the stability of the foundation pit in each construction stage is evaluated; According to the safety assessment results, construction optimization suggestions are generated, including support pile addition or soil reinforcement schemes; Provide risk warning information and real-time response measures for changes in the construction environment.

4. The finite element method-based simulation analysis method for foundation pits according to claim 1, characterized in that, The historical data and real-time monitoring data include: Soil settlement, groundwater flow level, vibration, and temperature sensor data during construction; Geological data, engineering design parameters, and construction monitoring results from historical foundation pit cases; The combination of historical data and real-time monitoring data improves and optimizes the simulation analysis process.

5. A foundation pit simulation analysis system based on a finite element method, characterized by, The finite element method-based foundation pit simulation analysis method of any one of claims 1-4 includes: Data acquisition module: This module uses geological exploration equipment, environmental monitoring sensors, climate monitoring equipment, groundwater level sensors, and settlement monitoring sensors to collect and store real-time data of foundation pit projects; Multi-physical field coupling modeling module: Based on the collected foundation pit project data, a multi-physical field coupling model including soil mechanics, groundwater flow, and heat conduction is established; Finite element analysis module: Based on the multi-physical field coupling model, the finite element method is used to simulate the mechanical behavior, groundwater flow, and thermal effects of the foundation pit; Nonlinear analysis and grid optimization module: Use the Mohr-Coulomb nonlinear constitutive model for soil nonlinear analysis, and optimize the finite element grid based on error estimation. This module automatically adjusts the grid density to ensure fine calculation in stress-concentrated areas while coarsening the grid in other areas; Deep learning optimization module: Use convolutional neural networks to learn historical data and real-time monitoring data, automatically optimize simulation model parameters; Cloud computing and parallel computing module: Based on the optimized model, use cloud computing platform for distributed parallel computing. It uses elastic computing resources to dynamically allocate tasks based on computing load, uses load balancing technology to ensure uniform load distribution among all computing nodes and avoid single-point overload; Report generation and optimization suggestion module: Generate a foundation pit safety assessment report based on the simulation results. The report includes stability analysis, construction risk assessment, and safety evaluation of each construction stage.

6. A foundation pit simulation analysis device based on a finite element method, characterized by, The finite element method-based foundation pit simulation analysis method of any one of claims 1-4 includes: Data acquisition equipment: including geological exploration equipment, environmental monitoring sensors, groundwater level sensors, and settlement monitoring sensors; Computing and simulation processing equipment: uses high-performance computer hardware, including processors, memory, and hard disk storage, supports efficient processing of parallel computing tasks; Cloud computing platform: provides a cloud platform with elastic computing resources, supporting cloud storage and computing; Deep learning processing unit: equipped with a deep learning processing unit for training convolutional neural networks and optimizing foundation pit simulation parameters; Output and feedback equipment: including display screen, printing equipment, and network interface, used to display simulation results and generate foundation pit safety assessment reports.

7. A computer-readable storage medium, characterized in that, A storage medium having stored thereon program code that, when executed by a computer, causes the computer to perform the finite element method-based foundation pit simulation analysis method according to any one of claims 1-4, and the storage medium comprises: data collection and storage instructions for controlling the data acquisition device to collect and store real-time data of the foundation pit project; multi-physical field coupling model construction instructions for constructing a multi-physical field coupling model of the foundation pit according to the collected foundation pit project data, and generating a coupling equation set; finite element simulation analysis instructions for performing finite element method simulation calculation on the basis of the constructed multi-physical field coupling model to obtain analysis results of stress, displacement and settlement; nonlinear finite element analysis and grid optimization instructions for accurately modeling the soil body using a nonlinear constitutive model and performing adaptive grid optimization according to the finite element simulation results; deep learning optimization instructions for learning historical data and real-time monitoring data using a convolutional neural network and automatically optimizing parameter settings of the simulation model; cloud computing and parallel computing optimization instructions for performing parallel computing through a cloud computing platform, distributing simulation tasks to multiple computing nodes, and ensuring fast processing of large-scale computing tasks.

Images