Methods, systems, smart terminals and storage media for predicting foundation pit deformation

Abstract

This application discloses a method, system, intelligent terminal, and storage medium for predicting foundation pit deformation, including: acquiring foundation pit measurement data and historical deformation monitoring data; constructing a finite element model of the foundation pit based on the measurement data; acquiring the parameters of the soil layer to be optimized and the first prediction depth; determining the first deformation prediction data through the finite element model of the foundation pit based on the parameters of the soil layer to be optimized and the first prediction depth, and determining the deformation prediction error corresponding to the parameters of the soil layer to be optimized by combining the historical deformation monitoring data; determining the parameters of the soil layer to be optimized for the next iteration based on the parameters of the soil layer to be optimized, and returning to execute the steps of determining the first deformation prediction data through the finite element model of the foundation pit based on the parameters of the soil layer to be optimized and the first prediction depth, until the parameter iteration termination condition is met, and determining the target soil layer parameters after optimization; determining the second deformation prediction data through the finite element model of the foundation pit based on the target soil layer parameters and the second prediction depth. This can reduce the computational workload of foundation pit deformation prediction.

Description

Technical Field

[0001] This application relates to the field of prediction technology in building engineering, and in particular to a method, system, intelligent terminal and storage medium for predicting foundation pit deformation. Background Technology

[0002] Currently, construction safety is receiving increasing attention, and foundation pit deformation is one of the important factors affecting the safe construction of foundation pit projects. In order to effectively ensure construction safety, it is necessary to determine the deformation of the foundation pit in a timely manner during the construction process.

[0003] In existing technologies, Bayesian methods are typically used for predicting foundation pit deformation. The problem with these existing technologies is that predicting foundation pit deformation using Bayesian methods requires relatively complex neural network models, resulting in a large computational load. This hinders efforts to reduce the computational burden during foundation pit deformation prediction and thus reduces the processing efficiency.

[0004] Therefore, the relevant technologies still need to be improved and developed. Summary of the Invention

[0005] The main objective of this application is to provide a method, system, smart terminal, and storage medium for predicting foundation pit deformation. The aim is to solve the technical problem that in related technologies, when predicting foundation pit deformation based on Bayesian methods, it is necessary to use a relatively complex neural network model, which results in a large amount of computation, making it difficult to reduce the amount of computation required for foundation pit deformation prediction and thus hindering the improvement of the processing efficiency of foundation pit deformation prediction.

[0006] To achieve the above objectives, the first aspect of this application provides a method for predicting the deformation of a foundation pit, wherein the method includes:

[0007] Obtain the foundation pit measurement data corresponding to the foundation pit, as well as the historical deformation monitoring data corresponding to the aforementioned foundation pit;

[0008] Based on the above foundation pit measurement data, construct the corresponding finite element model of the foundation pit;

[0009] Obtain the soil layer parameters to be optimized corresponding to the current iteration round, and the first predicted depth that matches the aforementioned historical deformation monitoring data;

[0010] Based on the above-mentioned soil layer parameters to be optimized and the above-mentioned first predicted depth, the first deformation prediction data of the above-mentioned foundation pit at the above-mentioned first predicted depth is determined by the above-mentioned foundation pit finite element model.

[0011] Based on the first deformation prediction data and the historical deformation monitoring data, the deformation prediction error corresponding to the soil layer parameters to be optimized is determined.

[0012] Based on the above-mentioned soil layer parameters to be optimized, determine the soil layer parameters to be optimized for the next iteration round, and return to execute the above-mentioned steps of determining the first deformation prediction data of the foundation pit at the first prediction depth based on the above-mentioned soil layer parameters to be optimized and the first prediction depth, through the above-mentioned foundation pit finite element model, until the preset parameter iteration termination condition is met, and determine the target soil layer parameters to be optimized based on the deformation prediction error corresponding to the soil layer parameters to be optimized in each iteration round.

[0013] Obtain the second predicted depth. Based on the target soil layer parameters and the second predicted depth, determine the second deformation prediction data of the foundation pit at the second predicted depth using the finite element model of the foundation pit.

[0014] Optionally, any iteration may correspond to multiple sets of soil layer parameters with different values;

[0015] Based on the soil layer parameters to be optimized and the first predicted depth, the first deformation prediction data of the foundation pit at the first predicted depth is determined using the finite element model of the foundation pit, including:

[0016] For each set of soil layer parameters to be optimized, based on the set of soil layer parameters to be optimized and the first predicted depth mentioned above, the first deformation prediction data corresponding to the set of soil layer parameters to be optimized is determined through the above-mentioned finite element model of the foundation pit.

[0017] Optionally, the deformation prediction error corresponding to the soil layer parameters to be optimized is determined based on the first deformation prediction data and the historical deformation monitoring data, including:

[0018] For each set of soil layer parameters to be optimized, the first deformation prediction data is used to determine the candidate prediction error corresponding to the set of soil layer parameters to be optimized based on the first deformation prediction data and the historical deformation monitoring data.

[0019] The smallest of all the above candidate prediction errors is taken as the deformation prediction error corresponding to the soil layer parameter to be optimized in the current iteration.

[0020] Optionally, for each set of soil layer parameters to be optimized, based on the first deformation prediction data and the historical deformation monitoring data, the candidate prediction error corresponding to that set of soil layer parameters to be optimized is determined, including:

[0021] For each set of soil layer parameters to be optimized, the first deformation prediction data is used to calculate the diaphragm wall deformation error and the surface settlement error based on the first deformation prediction data and the historical deformation monitoring data.

[0022] By weighted summing of the above-mentioned diaphragm wall deformation error and the above-mentioned surface settlement error, the candidate prediction error corresponding to the soil layer parameters to be optimized is obtained.

[0023] Optionally, the above-mentioned determination of the soil layer parameters to be optimized for the next iteration based on the aforementioned soil layer parameters to be optimized includes:

[0024] Obtain the parameter value range and parameter adjustment step size;

[0025] Based on the above-mentioned soil layer parameters to be optimized, the range of values ​​for the above-mentioned parameters, and the step size for adjusting the above-mentioned parameters, the soil layer parameters to be optimized for the next iteration are generated.

[0026] Optionally, the above-mentioned target soil layer parameters for optimization are determined based on the deformation prediction errors corresponding to the soil layer parameters to be optimized in each iteration round, including:

[0027] Determine the target iteration round that minimizes the deformation prediction error.

[0028] Based on the multiple sets of soil layer parameters to be optimized corresponding to the target iteration round with the minimum deformation prediction error, multiple sets of target soil layer parameters are determined.

[0029] Based on the target soil layer parameters and the second predicted depth, the aforementioned finite element model of the foundation pit determines the second deformation prediction data corresponding to the second predicted depth of the foundation pit, including:

[0030] The deformation prediction error values ​​corresponding to each set of target soil layer parameters are sorted, and at least one set of target calculation soil layer parameters is determined from the above multiple sets of target soil layer parameters based on the sorting results of the deformation prediction errors.

[0031] Based on the soil layer parameters and the second predicted depth mentioned above, the soil layer parameters and the above-mentioned second predicted depth are calculated according to the target group, and multiple candidate deformation prediction data are determined by the above-mentioned finite element model of the foundation pit.

[0032] The second deformation prediction data is determined based on all the above candidate deformation prediction data.

[0033] Optionally, the above methods also include:

[0034] Based on the aforementioned second deformation prediction data, a foundation pit deformation display diagram is generated and output.

[0035] The aforementioned second deformation prediction data includes lateral displacement information and depth information corresponding to multiple data points.

[0036] A second aspect of this application provides a foundation pit deformation prediction system, wherein the foundation pit deformation prediction system includes:

[0037] The first data acquisition module is used to acquire the foundation pit measurement data corresponding to the foundation pit, as well as the historical deformation monitoring data corresponding to the foundation pit.

[0038] The finite element model construction module is used to construct the finite element model of the foundation pit corresponding to the foundation pit based on the above foundation pit measurement data.

[0039] The second data acquisition module is used to acquire the soil layer parameters to be optimized corresponding to the current iteration round, as well as the first predicted depth that matches the aforementioned historical deformation monitoring data.

[0040] The first prediction module is used to determine the first deformation prediction data of the foundation pit at the first prediction depth based on the soil layer parameters to be optimized and the first prediction depth, using the finite element model of the foundation pit.

[0041] The error calculation module is used to determine the deformation prediction error corresponding to the above-mentioned soil layer parameters to be optimized based on the above-mentioned first deformation prediction data and the above-mentioned historical deformation monitoring data.

[0042] The iterative control module is used to determine the soil layer parameters to be optimized in the next iteration based on the soil layer parameters to be optimized, and return to execute the steps of determining the first deformation prediction data of the foundation pit at the first prediction depth based on the soil layer parameters to be optimized and the first prediction depth through the foundation pit finite element model, until the preset parameter iteration termination condition is met, and determine the target soil layer parameters to be optimized based on the deformation prediction error corresponding to the soil layer parameters to be optimized in each iteration.

[0043] The second prediction module is used to obtain the second prediction depth. Based on the target soil layer parameters and the second prediction depth, the module determines the second deformation prediction data of the foundation pit at the second prediction depth using the finite element model of the foundation pit.

[0044] A third aspect of this application provides a smart terminal, which includes a memory, a processor, and a foundation pit deformation prediction program stored in the memory and executable on the processor. When the foundation pit deformation prediction program is executed by the processor, it implements any of the steps of the foundation pit deformation prediction method.

[0045] A fourth aspect of this application provides a computer-readable storage medium storing a foundation pit deformation prediction program, wherein the foundation pit deformation prediction program, when executed by a processor, implements any of the steps of the foundation pit deformation prediction method.

[0046] As can be seen from the above, in this application, the following steps are taken: First, the foundation pit measurement data and historical deformation monitoring data corresponding to the foundation pit are obtained. Second, a finite element model of the foundation pit is constructed based on the foundation pit measurement data. Third, the soil layer parameters to be optimized for the current iteration are obtained, along with a first prediction depth matching the historical deformation monitoring data. Fourth, based on the soil layer parameters to be optimized and the first prediction depth, the first deformation prediction data corresponding to the foundation pit at the first prediction depth is determined using the foundation pit finite element model. Fifth, the deformation prediction error corresponding to the soil layer parameters to be optimized is determined based on the first deformation prediction data and the historical deformation monitoring data. The parameters of the soil layer to be optimized are determined, and the parameters of the soil layer to be optimized for the next iteration are determined. Then, the process of determining the first deformation prediction data of the foundation pit at the first prediction depth based on the parameters of the soil layer to be optimized and the first prediction depth is performed using the foundation pit finite element model is returned. This process continues until the preset parameter iteration termination condition is met. Based on the deformation prediction error of the parameters of the soil layer to be optimized in each iteration, the target soil layer parameters are determined. The second prediction depth is obtained, and the second deformation prediction data of the foundation pit at the second prediction depth is determined using the foundation pit finite element model based on the target soil layer parameters and the second prediction depth.

[0047] Compared with existing technologies, the foundation pit deformation prediction method provided in this application does not rely on complex neural network models, but instead is based on a foundation pit finite element model for deformation prediction. Specifically, the parameters of the soil layer to be optimized are optimized based on historical deformation monitoring data. After obtaining the optimized target soil layer parameters, foundation pit deformation prediction is performed based on the foundation pit finite element model. This helps reduce the computational load when predicting foundation pit deformation, thereby improving the processing efficiency of foundation pit deformation prediction. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart illustrating a method for predicting foundation pit deformation provided in an embodiment of this application;

[0050] Figure 2 This is a cross-sectional view of a foundation pit provided in an embodiment of this application;

[0051] Figure 3 This is a diagram illustrating the deformation of a foundation pit provided in an embodiment of this application;

[0052] Figure 4 This is another example of foundation pit deformation shown in the embodiments of this application;

[0053] Figure 5 This is another example of foundation pit deformation shown in the embodiments of this application;

[0054] Figure 6 This is another example of foundation pit deformation shown in the embodiments of this application;

[0055] Figure 7 This is another example of foundation pit deformation shown in the embodiments of this application;

[0056] Figure 8 This is a schematic diagram of the specific process of a foundation pit deformation prediction method provided in an embodiment of this application;

[0057] Figure 9 This is a schematic diagram of the constituent modules of a foundation pit deformation prediction system provided in an embodiment of this application;

[0058] Figure 10 This is a block diagram illustrating the internal structure of a smart terminal provided in an embodiment of this application. Detailed Implementation

[0059] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary detail.

[0060] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0061] It should also be understood that the terminology used in this application specification is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this application specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0062] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0063] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to classification." Similarly, the phrases "if determined" or "if classified to [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once classified to [the described condition or event]," or "in response to classification to [the described condition or event]."

[0064] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0065] Many specific details are set forth in the following description in order to provide a full understanding of this application. However, this application may also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0066] Currently, construction safety is receiving increasing attention, and the prediction of foundation pit deformation is also gaining importance. Supported excavation plays a crucial role in urban construction. However, this type of excavation presents complex problems in the interaction between soil and structure, involving foundation pit sidewall deflection and ground settlement, which can lead to damage to adjacent buildings and underground facilities. To ensure safe construction conditions, sidewall deflection and ground settlement for later excavation stages should be estimated before proceeding to the next stage. Overestimation increases construction costs, while underestimation makes excavation unsafe and may even cause accidents. Therefore, accurate and reliable prediction of sidewall deflection and ground movement is essential for good engineering practice. For example, it can help engineers make reliable decisions, thereby improving the safety, economy, and risk control of excavation operations.

[0067] In one application scenario, a phased update prediction method can be used to perform inverse analysis of soil parameters and then use the updated soil parameters to update the wall and / or ground response in subsequent excavation stages. In a specific application scenario, Bayesian methods can be used for foundation pit deformation prediction. Specifically, an update procedure based on a Bayesian probabilistic framework can be used for foundation pit deformation prediction. However, Bayesian methods for foundation pit deformation prediction require relatively complex neural network models, resulting in high computational load and complexity, which is not conducive to reducing the computational load and complexity of foundation pit deformation prediction and thus hinders the improvement of processing efficiency. Furthermore, during the Bayesian update process, the updated soil parameters can predict the maximum lateral displacement and maximum surface settlement, but the specific location corresponding to the maximum deformation and the accurate influence zone related to excavation-induced settlement cannot be predicted.

[0068] To address at least one of the aforementioned technical problems, the solution in this application involves: acquiring foundation pit measurement data and historical deformation monitoring data corresponding to the foundation pit; constructing a finite element model of the foundation pit based on the foundation pit measurement data; acquiring the soil layer parameters to be optimized for the current iteration and a first predicted depth matching the historical deformation monitoring data; determining the first predicted deformation data of the foundation pit at the first predicted depth using the foundation pit finite element model based on the soil layer parameters to be optimized and the first predicted depth; and determining the deformation corresponding to the soil layer parameters to be optimized based on the first predicted deformation data and the historical deformation monitoring data. Prediction error; Based on the above-mentioned soil layer parameters to be optimized, determine the soil layer parameters to be optimized for the next iteration, and return to execute the above-mentioned steps of determining the first deformation prediction data of the foundation pit at the first prediction depth based on the above-mentioned soil layer parameters to be optimized and the first prediction depth, through the above-mentioned foundation pit finite element model, until the preset parameter iteration termination condition is met, and determine the target soil layer parameters to be optimized based on the deformation prediction error corresponding to the soil layer parameters to be optimized in each iteration; obtain the second prediction depth, and determine the second deformation prediction data of the foundation pit at the second prediction depth based on the above-mentioned target soil layer parameters and the second prediction depth, through the above-mentioned foundation pit finite element model.

[0069] Compared with existing technologies, the foundation pit deformation prediction method provided in this application does not rely on complex neural network models, but instead predicts foundation pit deformation based on a finite element model. Specifically, the parameters of the soil layer to be optimized are obtained based on historical deformation monitoring data. After obtaining the optimized target soil layer parameters, foundation pit deformation is predicted based on the finite element model. This reduces the computational load and complexity of foundation pit deformation prediction, thereby improving the processing efficiency of foundation pit deformation prediction.

[0070] like Figure 1 As shown in the embodiment of this application, a method for predicting the deformation of a foundation pit is provided. Specifically, the method includes the following steps:

[0071] Step S100: Obtain the foundation pit measurement data corresponding to the foundation pit, as well as the historical deformation monitoring data corresponding to the foundation pit.

[0072] Specifically, in this application embodiment, the foundation pit refers to a foundation pit for which deformation prediction is required. The aforementioned foundation pit measurement data can characterize the corresponding soil and rock characteristics or properties, and the aforementioned historical deformation monitoring data are the foundation pit deformation monitoring data at each stage of construction.

[0073] During each stage of foundation pit construction, the deformation of the foundation pit is monitored in real time to obtain foundation pit deformation monitoring data. For example, if the foundation pit has been excavated to 10 meters at the current moment, the aforementioned historical deformation monitoring data can include the foundation pit deformation monitoring data corresponding to each stage up to 10 meters. The excavation depth corresponding to each stage can be determined according to the actual project excavation depth.

[0074] Step S200: Construct the finite element model of the foundation pit corresponding to the foundation pit based on the aforementioned foundation pit measurement data.

[0075] Figure 2 This is a cross-sectional view of a foundation pit provided in an embodiment of this application. It should be noted that the specific data shown in this embodiment of the application is based on on-site measurements of an ultra-deep foundation pit project.

[0076] It should be noted that the aforementioned foundation pit measurement data may include the foundation pit plan, measurement data on diaphragm wall deformation and surface settlement, parameters of the foundation pit support materials, the materials and parameters of the diaphragm walls, and relevant engineering geological data. This data is obtained through on-site monitoring and should cover key areas of the foundation pit, while also providing information on construction conditions for reference.

[0077] In one application scenario, the aforementioned foundation pit measurement data includes geotechnical data and engineering measurement data. Specifically, the aforementioned engineering measurement data may include one or more of the following parameters: the planar and cross-sectional dimensions of the foundation pit; the depth, thickness, unit weight, and elastic modulus of the diaphragm wall; the location, length, cross-sectional area, spacing, and elastic modulus of the support; the aforementioned geotechnical data may include one or more of the following parameters: the thickness of each soil layer and the basic physical and mechanical parameters of the soil layer (specifically including unit weight, internal friction angle, cohesion, water content, and permeability coefficient); and the groundwater level.

[0078] Based on the aforementioned geotechnical data and related engineering data, a corresponding finite element model of the foundation pit was established in the finite element analysis software Plaxis 2D. Furthermore, soil layers for which back-analysis optimization parameters need to be selected can be further selected. Specifically, the aforementioned foundation pit finite element model can predict the deformation of the foundation pit at a specified depth based on the input soil parameters.

[0079] It should be noted that the specific foundation pit measurement data required can be adjusted according to actual needs, and no specific limitations are made here. For missing specific foundation pit measurement data parameters, the default values ​​in the finite element analysis software can be used, and this is also not considered a specific limitation here.

[0080] In one application scenario, foundation pit deformation prediction is implemented based on corresponding code or programs. Specifically, the preprocessing and post-processing stages of the finite element analysis software are connected to the parameter optimization process in the main program. The preprocessing stage involves modeling and parameter setting in the finite element software, while the post-processing stage determines the foundation pit deformation prediction result based on the output of the foundation pit finite element model in the finite element analysis software. The main program is the core program used to implement the foundation pit deformation prediction function, including preliminary data processing (e.g., parameter format adjustment), parameter optimization, and final result output. The deformation prediction part is implemented by the main program calling the foundation pit finite element model in the finite element software.

[0081] Before running the main program, the code controlling the pre-processing and post-processing of the finite element analysis software is integrated into the main program. This allows subsequent runs to focus solely on the main program, with model parameter updates and post-processing data extraction handled automatically. Specifically, when running the main program, the Python code controlling the pre-processing and post-processing of the Plaxis 2D finite element analysis software is integrated into it. Subsequent runs only require running the main program, and each update of model parameters and extraction of post-processing data is performed automatically. The code integrated into the main program may vary depending on the finite element software used and can be set and adjusted according to actual needs; no specific limitations are specified here.

[0082] Step S300: Obtain the soil layer parameters to be optimized corresponding to the current iteration round, and the first predicted depth that matches the aforementioned historical deformation monitoring data.

[0083] It should be noted that if the current iteration is the initial iteration, the parameters of the soil layer to be optimized corresponding to the current iteration can be determined according to preset values. These preset values ​​can be input by the user in advance, or the default initial values ​​can be used, or a set of randomly generated initial values ​​can be used. No specific restrictions are made here.

[0084] If the current iteration is not the initial iteration, the soil layer parameters to be optimized in the current iteration are determined based on the soil layer parameters to be optimized in the previous iteration.

[0085] The aforementioned first predicted depth is used to control the final depth when the finite element model of the foundation pit makes predictions. Specifically, it is determined based on the deepest excavation depth corresponding to the historical deformation monitoring data. For example, if the historical deformation monitoring data includes foundation pit deformation monitoring data for each stage up to 10 meters, then the first predicted depth can be set to 10 meters, or it can be set to a value less than 10 meters. This application uses a setting of 10 meters as an example to fully utilize the historical deformation monitoring data, improve the accuracy of parameter optimization, and thus improve prediction accuracy.

[0086] Step S400: Based on the soil layer parameters to be optimized and the first predicted depth, the first deformation prediction data of the foundation pit at the first predicted depth is determined using the finite element model of the foundation pit.

[0087] In one application scenario, the finite element model of the foundation pit, based on the aforementioned soil layer parameters to be optimized and the aforementioned first predicted depth, calculates and outputs the first deformation prediction data matched for multiple different excavation stages (each excavation stage corresponds to a different excavation depth), including the first predicted depth. Specifically, the first deformation prediction data only includes the deformation prediction data corresponding to the excavation to the first predicted depth and the multiple excavation stages before reaching the first predicted depth. In this case, error calculation can be performed based on the foundation pit deformation monitoring data corresponding to each stage from historical deformation monitoring data. This further improves the accuracy of error calculation, thereby enhancing the parameter optimization effect and ultimately improving the final prediction effect.

[0088] Specifically, each iteration corresponds to multiple sets of soil layer parameters with different values;

[0089] Based on the soil layer parameters to be optimized and the first predicted depth, the first deformation prediction data of the foundation pit at the first predicted depth is determined using the finite element model of the foundation pit, including:

[0090] For each set of soil layer parameters to be optimized, based on the set of soil layer parameters to be optimized and the first predicted depth mentioned above, the first deformation prediction data corresponding to the set of soil layer parameters to be optimized is determined through the above-mentioned finite element model of the foundation pit.

[0091] The number of sets of soil parameters to be optimized for each iteration can be set and adjusted according to actual needs. For example, it can be set to 50 sets of soil parameters to be optimized for one generation. Each set of soil parameters to be optimized is a complete set of parameters, including all the soil parameters required for the finite element model calculation of the foundation pit. The categories of soil parameters to be optimized are the same across different sets, only their values ​​differ.

[0092] Specifically, initially, the soil layer parameters to be optimized are input into the optimization program, and these parameters are configured (i.e., initialized) in the main program, while the error calculation function is set. In this embodiment, the constitutive model selected for the soil is the small strain soil hardening (HSS, HS-Small) model, and the selected parameters to be optimized include: μ and small strain parameters and γ 0.7 The soil layers requiring optimization include silty clay and clay layers, thus involving a total of 12 parameters. In other words, a set of soil layer parameters to be optimized includes 12 parameters. Represents tangent modulus; Represents the secant modulus. This represents the unloading and reloading modulus, where μ represents Poisson's ratio. Represents the initial shear modulus, γ 0.7 This represents shear strain. Specifically, it can be... Figure 2 Layers ②, ③, and ④, with similar compressibility coefficients, merged into a single layer of silty clay. Figure 2 The clay and silty clay layers in layer ⑤, which have similar compressibility coefficients, merge into a single clay layer.

[0093] It should be noted that the soil layers selected for optimization of back analysis parameters in this application embodiment are those with large thickness, high compressibility, and are easily disturbed by surrounding construction, leading to a decrease in soil strength. These include soil layers above and below the bottom of the foundation pit. This application embodiment uses the above two types of soil layers as examples for specific illustration, but this is not intended to limit the scope of the application.

[0094] Step S500: Based on the first deformation prediction data and the historical deformation monitoring data, determine the deformation prediction error corresponding to the soil layer parameters to be optimized.

[0095] Specifically, based on the aforementioned first deformation prediction data and the aforementioned historical deformation monitoring data, the deformation prediction error corresponding to the aforementioned soil layer parameters to be optimized is determined, including:

[0096] For each set of soil layer parameters to be optimized, the first deformation prediction data is used to determine the candidate prediction error corresponding to the set of soil layer parameters to be optimized based on the first deformation prediction data and the historical deformation monitoring data.

[0097] The smallest of all the above candidate prediction errors is taken as the deformation prediction error corresponding to the soil layer parameter to be optimized in the current iteration.

[0098] Furthermore, for each set of soil layer parameters to be optimized, based on the first deformation prediction data and the historical deformation monitoring data, the candidate prediction error corresponding to that set of soil layer parameters to be optimized is determined, including:

[0099] For each set of soil layer parameters to be optimized, the first deformation prediction data is used to calculate the diaphragm wall deformation error and the surface settlement error based on the first deformation prediction data and the historical deformation monitoring data.

[0100] By weighted summing of the above-mentioned diaphragm wall deformation error and the above-mentioned surface settlement error, the candidate prediction error corresponding to the soil layer parameters to be optimized is obtained.

[0101] The weight values ​​corresponding to the above-mentioned diaphragm wall deformation error and the above-mentioned surface settlement error can be set and adjusted according to actual needs, and are not specifically limited here.

[0102] It should be noted that when determining the error between the monitoring data and the predicted data, the difference between the corresponding deformation monitoring value and the deformation predicted value can be directly used as the error value, or the corresponding error value can be determined based on a preset error calculation function. No specific limitation is made here. The aforementioned error calculation function can be set and adjusted according to actual needs.

[0103] For supported excavation, diaphragm wall deformation and surface settlement are two extremely important indicators reflecting the impact of soil-structure interaction on excavation. After completing the finite element calculation, the required data are extracted, and the data of diaphragm wall deformation and surface settlement monitored in previous stages are imported. The imported monitoring data are interpolated to ensure that the coordinates of each data point match the coordinates of the data extracted from the calculation results. The error between the simulation results and the monitoring data of each stage is calculated. The error calculation formula between the simulation results and the monitoring data of each stage is shown in the following formula (1):

[0104]

[0105] Where x represents a set of soil parameters to be optimized in one iteration, Error(x) represents the candidate prediction error corresponding to the set of soil parameters to be optimized, and n is the number of observation points (i.e., data points). This represents the value corresponding to the i-th observation point in the historical deformation monitoring data. This represents the value corresponding to the i-th observation point in the first deformation prediction data. This represents the maximum deformation value for the current stage in the historical deformation monitoring data. It should be noted that if the historical deformation monitoring data includes data corresponding to multiple excavation stages, then... This represents the maximum deformation value at the current calculation stage. For example, if the first predicted depth is the depth when excavating to the third stage, then... This is the maximum deformation value during the third stage of excavation. It should be noted that the error value calculated directly may be small. To facilitate subsequent calculations, this embodiment of the application also multiplies it by 100 to adjust the error value and facilitate subsequent calculations.

[0106] In one application scenario, the formula for calculating the deformation prediction error is shown in the following formula (2):

[0107] min[Error(x)] = min[Error wall (x)×w1+Error ground [(x)×w2] (2);

[0108] Where min[Error(x)] represents the smallest candidate prediction error in a single iteration, i.e., the deformation prediction error in that iteration. x represents a set of soil layer parameters to be optimized in that iteration. wall (x) represents the deformation error of the diaphragm wall, and w1 represents its corresponding weight value; Error ground (x) represents the surface settlement error, and w2 represents its corresponding weight value; the two can be assigned corresponding weight values ​​according to actual needs, and no specific restrictions are made here.

[0109] It should be noted that the specific calculation methods for diaphragm wall deformation error and ground surface settlement error can refer to the above formula (1). For example, when calculating the diaphragm wall deformation error, the corresponding sidewall deformation data are extracted from the first deformation prediction data and historical deformation monitoring data, and the calculation is performed based on the above formula (1).

[0110] In one application scenario, after calculating the error between the simulation results and the monitoring data at each stage, further calculations can be performed based on the errors corresponding to each stage, as shown in formulas (3) and (4) below:

[0111] Error wall (x)=Error1(x)+Error2(x)+...+Error m (x) (3);

[0112] Error ground (x)=Error1(x2)+Error2(x2)+...+Error m (x2) (4);

[0113] Among them, Error wall Error(x) is the sum of the errors in each stage of the diaphragm wall construction, and Error1(x) is the error in the first stage of the diaphragm wall construction. m (x) represents the diaphragm wall error at the m-th stage, where m is the number of target excavation stages involved in the error calculation. Similarly, Error ground (x) is the sum of surface subsidence errors at each stage, and Error1(x2) is the surface subsidence error at the first stage. m (x2) is the surface subsidence error in the m-th stage.

[0114] Step S600: Based on the above-mentioned soil layer parameters to be optimized, determine the soil layer parameters to be optimized for the next iteration round, and return to execute the above-mentioned step of determining the first deformation prediction data of the foundation pit at the first prediction depth based on the above-mentioned soil layer parameters to be optimized and the first prediction depth through the above-mentioned foundation pit finite element model, until the preset parameter iteration termination condition is met, and determine the target soil layer parameters to be optimized based on the deformation prediction error corresponding to the soil layer parameters to be optimized in each iteration round.

[0115] Specifically, based on the aforementioned soil layer parameters to be optimized, the parameters to be optimized for the next iteration are determined, including:

[0116] Obtain the parameter value range and parameter adjustment step size;

[0117] Based on the above-mentioned soil layer parameters to be optimized, the range of values ​​for the above-mentioned parameters, and the step size for adjusting the above-mentioned parameters, the soil layer parameters to be optimized for the next iteration are generated.

[0118] The parameter value range and parameter adjustment step size mentioned above can be set and adjusted according to actual needs. If the parameter value range is greater than the parameter limit range determined in advance based on experiments, the optimization program will optimize the parameters within this range and make adjustments based on a reasonable parameter adjustment step size.

[0119] In one application scenario, based on the soil layer parameters to be optimized, within the range of the above parameter values, the adjustment step size of the above parameters is used as the minimum adjustment step size (or the maximum adjustment step size), and the soil layer parameters to be optimized for the next iteration are randomly generated, or the parameters are adjusted at equal intervals to generate the soil layer parameters to be optimized for the next iteration. Other parameter generation methods can also be used, which are not specifically limited here.

[0120] Specifically, the aforementioned preset parameter iteration termination conditions include the number of iterations reaching a preset iteration threshold and / or the deformation prediction error being less than a preset error threshold. It should be noted that the aforementioned iteration threshold and error threshold can be set and adjusted according to actual needs. In this embodiment, to reduce computational costs, the iteration threshold is set to 50-70 times, but this is not a specific limitation.

[0121] In a specific application scenario, soil layer parameter optimization is performed according to the following steps: The main optimization program is run, parameters are initialized, and the soil layer parameters to be optimized in the foundation pit model are updated. The program runs finite element analysis software, and after completing the finite element calculation, it automatically extracts the diaphragm wall deformation and surface settlement data from the calculation results, and imports foundation pit deformation monitoring data from each construction stage, including diaphragm wall deformation and surface settlement. The error between the simulation results and the monitoring data from each construction stage is calculated, and the parameters are optimized to minimize the error. The program will continue to iterate and generate new parameters until the criteria for stopping iteration are met. Specifically, within a set range, a new generation of parameters is randomly generated. In each generation of parameters, after calculation, parameters with large errors are eliminated, and multiple sets of parameters with small errors are selected to continue iterating and generating a new generation of parameters, minimizing the error.

[0122] Step S700: Obtain the second predicted depth. Based on the target soil layer parameters and the second predicted depth, determine the second deformation prediction data of the foundation pit at the second predicted depth using the finite element model of the foundation pit.

[0123] Specifically, based on the deformation prediction error corresponding to the soil layer parameters to be optimized in each iteration, the target soil layer parameters for optimization are determined, including:

[0124] Determine the target iteration round that minimizes the deformation prediction error.

[0125] Based on the multiple sets of soil layer parameters to be optimized corresponding to the target iteration round with the minimum deformation prediction error, multiple sets of target soil layer parameters are determined.

[0126] Based on the target soil layer parameters and the second predicted depth, the aforementioned finite element model of the foundation pit determines the second deformation prediction data corresponding to the second predicted depth of the foundation pit, including:

[0127] The deformation prediction error values ​​corresponding to each set of target soil layer parameters are sorted, and at least one set of target calculation soil layer parameters is determined from the above multiple sets of target soil layer parameters based on the sorting results of the deformation prediction errors.

[0128] Based on the soil layer parameters and the second predicted depth mentioned above, the soil layer parameters and the above-mentioned second predicted depth are calculated according to the target group, and multiple candidate deformation prediction data are determined by the above-mentioned finite element model of the foundation pit.

[0129] The second deformation prediction data is determined based on all the above candidate deformation prediction data.

[0130] The second predicted depth is the actual excavation depth that needs to be predicted, and it can be set and adjusted according to actual needs. That is, in this embodiment of the application, the deformation of the foundation pit is predicted to predict the deformation of the foundation pit when it is excavated to the second predicted depth (for example, the next construction stage corresponds to the second predicted depth).

[0131] In this embodiment of the application, the generation of soil layer parameters to be optimized with the smallest deformation prediction error (including multiple sets of soil layer parameters to be optimized) is taken as the target soil layer parameters after optimization corresponding to the target iteration round.

[0132] In one application scenario, the second deformation prediction data can be determined by calculating based on all target soil layer parameters of the target iteration round. In this embodiment, to further reduce the computational load, a portion of the target calculation soil layer parameters are selected from all target soil layer parameters of the target iteration round for calculation. It should be noted that the number of selected target calculation soil layer parameters can be set and adjusted according to actual needs. For example, in this embodiment, the parameters with the smallest deformation prediction error values ​​in the top 30% of all target soil layer parameters of the target iteration round are selected as the target calculation soil layer parameters, that is, the number of groups of target calculation soil layer parameters is 30% of the number of target soil layer parameter groups in the target iteration round. The average value of the candidate deformation prediction data corresponding to each group of target calculation soil layer parameters is then used as the final second deformation prediction data.

[0133] It should be noted that in this embodiment, multiple sets of target calculated soil layer parameters are used to calculate the second deformation prediction data. In addition to calculating the mean of the candidate deformation prediction data corresponding to each set of target calculated soil layer parameters, the corresponding variance can also be calculated to better illustrate the deformation situation. Specifically, the foundation pit deformation in the calculation results can also be extracted, and the average value and variance of the deformation can be plotted for comprehensive evaluation.

[0134] In this embodiment of the application, the above method further includes:

[0135] Based on the aforementioned second deformation prediction data, a foundation pit deformation display diagram is generated and output.

[0136] The aforementioned second deformation prediction data includes lateral displacement information and depth information corresponding to multiple data points.

[0137] Specifically, the above-mentioned foundation pit deformation diagram can be drawn based on the specific deformation situation in the second deformation prediction data. Figure 3 This is a diagram illustrating the deformation of a foundation pit provided in an embodiment of this application. It should be noted that... Figure 3 The image shows the lateral deformation curve of the diaphragm wall, and Figure 3 The diagram shows the lateral deformation curves of the diaphragm wall corresponding to multiple excavation stages. For example, Excavation 2 represents the second stage of excavation, which corresponds to the two excavations. Similarly, Excavation 3 represents the third stage of excavation, and so on. Figure 3 In the text, C6 represents the name of the location of the sixth deformation monitoring point of the diaphragm wall in the foundation pit.

[0138] It should be noted that the deformation display diagram of the foundation pit can also only show the predicted deformation curves corresponding to the stages that need to be predicted. Figures 4 to 7 This is a diagram illustrating the deformation of the foundation pit provided in an embodiment of this application. Specifically, Figures 4 to 7 The diagram shows a predicted lateral deformation curve of the diaphragm wall with error bars. In this embodiment, deformation prediction begins after the third excavation and continues until the final excavation depth is reached. For example, if the first prediction involves excavation to 10 meters, a prediction is made for 15 meters; then, when the actual excavation reaches 15 meters, the deformation corresponding to 20 meters can be predicted, until the final excavation depth is reached. It should be noted that this embodiment uses an excavation depth of 5 meters as an example for illustration. Figure 4 The diagram shows a comparison between predicted and monitoring data for the fourth stage of excavation. Figure 5 The diagram shows a comparison between predicted and monitoring data for the fifth stage of excavation. Figure 6 The diagram shows a comparison between predicted and monitoring data for the sixth stage of excavation. Figure 7 The diagram shows a comparison between predicted and monitored data for the seventh stage of excavation. It should be noted that the simulation was performed using PLAXIS 2D software; the first 30% of multiple parameter sets from the first generation with the smallest error were used for calculation. After the calculation, the diaphragm wall deformation was extracted, and their mean and variance were calculated.

[0139] It should be further noted that the specific format of the foundation pit deformation display diagram can be set and adjusted according to actual needs, and no specific limitation is made here.

[0140] As can be seen from the above, the foundation pit deformation prediction method provided in this application involves: acquiring foundation pit measurement data and historical deformation monitoring data corresponding to the foundation pit; constructing a foundation pit finite element model based on the foundation pit measurement data; acquiring the soil layer parameters to be optimized corresponding to the current iteration and the first prediction depth matching the historical deformation monitoring data; determining the first deformation prediction data corresponding to the foundation pit at the first prediction depth using the foundation pit finite element model based on the soil layer parameters to be optimized and the first prediction depth; and determining the deformation prediction error corresponding to the soil layer parameters to be optimized based on the first deformation prediction data and the historical deformation monitoring data. The process continues: Based on the soil parameters to be optimized, the parameters to be optimized for the next iteration are determined, and the process returns to the previous steps of determining the first deformation prediction data of the foundation pit at the first prediction depth using the finite element model of the foundation pit, based on the soil parameters to be optimized and the first prediction depth, until the preset parameter iteration termination condition is met. Based on the deformation prediction error of the soil parameters to be optimized in each iteration, the target soil parameters are determined; the second prediction depth is obtained, and based on the target soil parameters and the second prediction depth, the second deformation prediction data of the foundation pit at the second prediction depth is determined using the finite element model of the foundation pit.

[0141] Compared with existing technologies, the foundation pit deformation prediction method provided in this application does not rely on complex neural network models, but instead predicts foundation pit deformation based on a finite element model. Specifically, the parameters of the soil layer to be optimized are optimized based on historical deformation monitoring data. After obtaining the optimized target soil layer parameters, foundation pit deformation prediction is performed based on the finite element model. This helps reduce the computational load and complexity when predicting foundation pit deformation, thereby improving the processing efficiency of foundation pit deformation prediction.

[0142] In this embodiment of the application, the above-mentioned foundation pit deformation prediction method is further described in detail based on a specific application scenario. Figure 8 This is a schematic flowchart illustrating a method for predicting foundation pit deformation provided in an embodiment of this application. Specifically, as shown... Figure 8As shown in the embodiment of this application, firstly, foundation pit measurement data and historical deformation monitoring data are acquired. A finite element model of the foundation pit is constructed based on the measurement data, and the parameters of the soil layer to be optimized are determined. The parameters of the soil layer to be optimized are initialized, and based on the foundation pit finite element model, a prediction is made for the first predicted depth according to the parameters of the soil layer to be optimized. The error is evaluated based on the prediction results and historical deformation monitoring data, and it is determined whether the parameter iteration termination condition is met. If not, the parameters of the soil layer to be optimized are optimized and updated, and the prediction at the first predicted depth is repeated to achieve iterative update of the parameters. Conversely, if the parameter iteration termination condition is met, the optimized target soil layer parameters are determined, and a corresponding prediction is made for the second predicted depth.

[0143] The process from parameter initialization to prediction at the second prediction depth can be executed by the main program. During operation, the main program can automatically call the finite element model of the foundation pit for corresponding predictions. Specifically, when predicting and evaluating errors, simulation calculations are performed, finite element calculations are conducted based on the currently input soil layer parameters to be optimized, and the necessary post-processing data (including the first deformation prediction data) is extracted. The error is then calculated based on the first deformation prediction data and historical deformation monitoring data.

[0144] It should be noted that the aforementioned preset parameter iteration termination conditions may include the number of iterations reaching a preset iteration threshold and / or the deformation prediction error being less than a preset error threshold. The deformation prediction error can be determined based on each group of soil layer parameters to be optimized in one generation, or it can be determined solely based on the top 30% of the corresponding candidate prediction errors in one generation (the specific value can be set and adjusted according to actual needs).

[0145] Thus, in this embodiment, the soil layer parameters of the model are optimized based on on-site measurement data during the excavation process. Using these optimized parameters, the wall deflection and surface settlement in the subsequent unexcavated stage are predicted. Repeating the above steps allows for prediction of excavation deformation throughout the entire excavation process. Furthermore, this method can be applied to actual segmented excavation and combined with on-site data to predict deformation in subsequent stages.

[0146] The foundation pit deformation prediction method provided in this application can accurately predict the maximum deformation value and its location during excavation. Its core principle involves constructing a corresponding foundation pit model in finite element software and selecting key soil layer parameters, which are then optimized in subsequent back analysis. By running the optimization program, the optimized back analysis parameters can be considered as the actual parameters of the soil that cause foundation pit deformation during actual construction. These parameters are then fed back into the finite element model, updating the corresponding parameters for simulation calculation. By analyzing the simulation results, the deformation data that may occur in the foundation pit during the next construction stage can be extracted. Furthermore, by utilizing the foundation pit deformation data monitored during the current construction stage, the deformation situation of the foundation pit in the next stage can be predicted. This method improves the accuracy of prediction, thereby providing a more reliable scientific basis for construction safety.

[0147] like Figure 9 As shown in the figure, corresponding to the above-mentioned foundation pit deformation prediction method, this application embodiment also provides a foundation pit deformation prediction system, the foundation pit deformation prediction system comprising:

[0148] The first data acquisition module 910 is used to acquire the foundation pit measurement data corresponding to the foundation pit, as well as the historical deformation monitoring data corresponding to the foundation pit.

[0149] Finite element model construction module 920 is used to construct the finite element model of the foundation pit corresponding to the foundation pit based on the above foundation pit measurement data;

[0150] The second data acquisition module 930 is used to acquire the soil layer parameters to be optimized corresponding to the current iteration round, as well as the first predicted depth that matches the aforementioned historical deformation monitoring data.

[0151] The first prediction module 940 is used to determine the first deformation prediction data of the foundation pit at the first prediction depth based on the soil layer parameters to be optimized and the first prediction depth, using the foundation pit finite element model.

[0152] The error calculation module 950 is used to determine the deformation prediction error corresponding to the above-mentioned soil layer parameters to be optimized based on the above-mentioned first deformation prediction data and the above-mentioned historical deformation monitoring data.

[0153] The iteration control module 960 is used to determine the soil layer parameters to be optimized in the next iteration based on the soil layer parameters to be optimized, and return to execute the steps of determining the first deformation prediction data of the foundation pit at the first prediction depth based on the soil layer parameters to be optimized and the first prediction depth through the foundation pit finite element model, until the preset parameter iteration termination condition is met, and determine the target soil layer parameters to be optimized based on the deformation prediction error of the soil layer parameters to be optimized in each iteration.

[0154] The second prediction module 970 is used to obtain the second prediction depth. Based on the target soil layer parameters and the second prediction depth, the module determines the second deformation prediction data of the foundation pit at the second prediction depth using the finite element model of the foundation pit.

[0155] Therefore, the solution provided in this application does not rely on complex neural network models, but instead predicts foundation pit deformation based on a finite element model. Specifically, the parameters of the soil layer to be optimized are optimized based on historical deformation monitoring data. After obtaining the optimized target soil layer parameters, foundation pit deformation is predicted based on the finite element model. This helps reduce the computational load and complexity when predicting foundation pit deformation, thereby improving the processing efficiency of foundation pit deformation prediction.

[0156] It should be noted that the specific structure and implementation of the above-mentioned foundation pit deformation prediction system and its various modules or units can be referred to the corresponding descriptions in the above method embodiments, and will not be repeated here.

[0157] It should be noted that the division of the various modules of the above-mentioned foundation pit deformation prediction system is not unique and is not intended as a specific limitation.

[0158] Based on the above embodiments, this application also provides a smart terminal, the principle block diagram of which can be as follows: Figure 10 As shown. The aforementioned intelligent terminal includes a processor, memory, network interface, and display screen connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and the foundation pit deformation prediction program. The internal memory provides an environment for the operation of the operating system and the foundation pit deformation prediction program stored in the non-volatile storage medium. The network interface of the intelligent terminal is used for communication with external terminals via a network connection. When the foundation pit deformation prediction program is executed by the processor, it implements the steps of any of the aforementioned foundation pit deformation prediction methods. The display screen of the intelligent terminal can be a liquid crystal display (LCD) or an e-ink display.

[0159] Those skilled in the art will understand that Figure 10 The block diagram shown is only a partial structural diagram related to the solution of this application and does not constitute a limitation on the smart terminal on which the solution of this application is applied. The specific smart terminal may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0160] In one embodiment, a smart terminal is provided, the smart terminal including a memory, a processor, and a foundation pit deformation prediction program stored in the memory and executable on the processor. When the foundation pit deformation prediction program is executed by the processor, it implements the steps of any foundation pit deformation prediction method provided in the embodiments of this application.

[0161] This application also provides a computer-readable storage medium storing a foundation pit deformation prediction program. When the foundation pit deformation prediction program is executed by a processor, it implements the steps of any foundation pit deformation prediction method provided in this application.

[0162] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0163] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the above device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0164] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0165] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0166] In the embodiments provided in this application, it should be understood that the disclosed systems / terminal devices and methods can be implemented in other ways. For example, the system / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units described above is merely a logical functional division, and in actual implementation, it can be divided in other ways. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0167] If the integrated modules / units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, and software distribution media, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0168] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions are not in essence a departure from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method of predicting deformation of a foundation pit, characterized by, The method comprises: obtaining foundation pit measurement data corresponding to a foundation pit, and historical deformation monitoring data corresponding to the foundation pit; constructing a foundation pit finite element model corresponding to the foundation pit according to the foundation pit measurement data; obtaining to-be-optimized soil layer parameters corresponding to a current iteration round, and a first predicted depth matched with the historical deformation monitoring data; determining, according to the to-be-optimized soil layer parameters and the first predicted depth, first deformation prediction data corresponding to the foundation pit at the first predicted depth through the foundation pit finite element model; determining a deformation prediction error corresponding to the to-be-optimized soil layer parameters according to the first deformation prediction data and the historical deformation monitoring data; determining to-be-optimized soil layer parameters corresponding to a next iteration round according to the to-be-optimized soil layer parameters, and returning to perform the step of determining, according to the to-be-optimized soil layer parameters and the first predicted depth, first deformation prediction data corresponding to the foundation pit at the first predicted depth through the foundation pit finite element model until a preset parameter iteration termination condition is met, and determining target soil layer parameters of which optimization is completed according to deformation prediction errors corresponding to to-be-optimized soil layer parameters in each iteration round, wherein the preset parameter iteration termination condition comprises that an iteration number reaches a preset iteration threshold and / or a deformation prediction error is smaller than a preset error threshold; obtaining a second predicted depth, and determining, according to the target soil layer parameters and the second predicted depth, second deformation prediction data corresponding to the foundation pit at the second predicted depth through the foundation pit finite element model.

2. The foundation deformation prediction method according to claim 1, characterized by, Any iteration round corresponds to a plurality of groups of to-be-optimized soil layer parameters with different values; The step of determining, according to the to-be-optimized soil layer parameters and the first predicted depth, first deformation prediction data corresponding to the foundation pit at the first predicted depth through the foundation pit finite element model comprises: for each group of to-be-optimized soil layer parameters, determining, according to the group of to-be-optimized soil layer parameters and the first predicted depth, first deformation prediction data corresponding to the group of to-be-optimized soil layer parameters through the foundation pit finite element model.

3. The foundation deformation prediction method according to claim 2, characterized by, The step of determining a deformation prediction error corresponding to the to-be-optimized soil layer parameters according to the first deformation prediction data and the historical deformation monitoring data comprises: for first deformation prediction data corresponding to each group of to-be-optimized soil layer parameters, determining a candidate prediction error corresponding to the group of to-be-optimized soil layer parameters according to the first deformation prediction data and the historical deformation monitoring data; taking the minimum of all the candidate prediction errors as the deformation prediction error corresponding to the to-be-optimized soil layer parameters of the current iteration round.

4. The foundation deformation prediction method according to claim 3, characterized by, The step of determining, for first deformation prediction data corresponding to each group of to-be-optimized soil layer parameters, a candidate prediction error corresponding to the group of to-be-optimized soil layer parameters according to the first deformation prediction data and the historical deformation monitoring data comprises: for first deformation prediction data corresponding to each group of to-be-optimized soil layer parameters, calculating a diaphragm wall deformation error and a ground surface settlement error according to the first deformation prediction data and the historical deformation monitoring data; performing weighted summation on the diaphragm wall deformation error and the ground surface settlement error to obtain a candidate prediction error corresponding to the group of to-be-optimized soil layer parameters.

5. The foundation deformation prediction method according to claim 1, characterized by, The method further comprises: generating a foundation pit deformation display diagram according to the second deformation prediction data, and outputting the foundation pit deformation display diagram; wherein the second deformation prediction data comprises lateral displacement information and depth information corresponding to a plurality of data points.

6. The foundation deformation prediction method according to claim 3, characterized by, The system comprises: a first data acquisition module configured to acquire foundation pit measurement data corresponding to a foundation pit and historical deformation monitoring data corresponding to the foundation pit; a finite element model construction module configured to construct a foundation pit finite element model corresponding to the foundation pit according to the foundation pit measurement data; a second data acquisition module configured to acquire a to-be-optimized soil layer parameter corresponding to a current iteration round and a first predicted depth matched with the historical deformation monitoring data; a first prediction module configured to determine first deformation prediction data corresponding to the foundation pit at the first predicted depth by the foundation pit finite element model according to the to-be-optimized soil layer parameter and the first predicted depth; an error calculation module configured to determine deformation prediction error corresponding to the to-be-optimized soil layer parameter according to the first deformation prediction data and the historical deformation monitoring data; 7. The foundation deformation prediction method according to claim 1, characterized by, an iteration control module configured to determine a to-be-optimized soil layer parameter corresponding to a next iteration round according to the to-be-optimized soil layer parameter, and return to execute the step of determining first deformation prediction data corresponding to the foundation pit at the first predicted depth by the foundation pit finite element model according to the to-be-optimized soil layer parameter and the first predicted depth until a preset parameter iteration termination condition is met, and determine a target soil layer parameter optimized according to deformation prediction error corresponding to the to-be-optimized soil layer parameter in each iteration round, wherein the preset parameter iteration termination condition comprises that an iteration number reaches a preset iteration threshold and / or deformation prediction error is less than a preset error threshold; and a target soil layer parameter determination module configured to determine a target iteration round with minimum deformation prediction error, and determine a plurality of target soil layer parameters according to a plurality of to-be-optimized soil layer parameters corresponding to the target iteration round with minimum deformation prediction error. The system further comprises:

8. A foundation pit deformation prediction system characterized by, a target calculation soil layer parameter determination module configured to sort values of deformation prediction error corresponding to each target soil layer parameter, and determine at least one target calculation soil layer parameter from the plurality of target soil layer parameters according to a sorting result of deformation prediction error; a candidate deformation prediction data determination module configured to determine a plurality of candidate deformation prediction data by the foundation pit finite element model according to each target calculation soil layer parameter and the second predicted depth; a second deformation prediction data determination module configured to determine the second deformation prediction data according to all the candidate deformation prediction data. The system further comprises: a foundation pit deformation display diagram generation module configured to generate a foundation pit deformation display diagram according to the second deformation prediction data, and output the foundation pit deformation display diagram; wherein the second deformation prediction data comprises lateral displacement information and depth information corresponding to a plurality of data points. ​ A second prediction module is configured to obtain a second predicted depth, and determine second deformation prediction data of the foundation pit corresponding to the second predicted depth by the finite element model of the foundation pit according to the target soil layer parameter and the second predicted depth.

9. A smart terminal, characterized by The intelligent terminal comprises a memory, a processor, and a foundation pit deformation prediction program stored in the memory and executable on the processor. When the foundation pit deformation prediction program is executed by the processor, the steps of the foundation pit deformation prediction method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a foundation pit deformation prediction program. When the foundation pit deformation prediction program is executed by the processor, the steps of the foundation pit deformation prediction method according to any one of claims 1 to 7 are implemented.

Images