A method, device, equipment and medium for predicting construction deformation of deep foundation pit construction

Abstract

The present application provides a method, device, equipment and medium for predicting construction deformation of deep foundation pit construction, wherein the method includes: obtaining survey data and construction design data of the target engineering area; determining an orthogonal test scheme according to the distribution data of the confined water layer in the target engineering area; numerically simulating the working conditions of each construction method in the construction design data to determine the deformation value under each working condition; performing multivariate linear analysis according to the orthogonal test scheme, the deformation value under the working condition of each construction method and the distribution data of the confined water layer in the target engineering area to determine the relationship between the construction deformation of each construction method in each stage of deep foundation pit construction in the target engineering area and the distribution of the confined water layer in the target engineering area. Achieve a good grasp of the deformation of foundation pit construction, and use it to guide the optimization construction of deep foundation pits.

Description

Technical Field

[0001] The present application relates to the field of intelligent construction technology, and more specifically, to a method, device, equipment and medium for predicting construction deformation in deep foundation pit construction. Background Art

[0002] At present, with the application and development of artificial intelligence technology in civil engineering construction, the current development of informatization and automation has made the construction of deep foundation pit engineering gradually systematic and orderly; although mechanized construction is highly efficient, the construction cost is high, the specific construction situation is complex, and it is difficult to achieve a good deformation control effect. The shift in construction focus has also become prominent, especially the grasp of the construction situation of deep foundation pits in confined water strata is very important. Among them, the deformation of deep foundation pit construction in multi-layer confined water strata is mainly affected by factors such as stratum properties, confined water layer characteristics, and construction methods; in soft and water-rich strata, the distribution and pressure of confined water have a great influence on the structure of deep foundation pits. It can be seen that the reasonable grasp of confined water and construction methods is the premise for the safe and optimized construction of deep foundation pits. Therefore, it is imperative to propose a technology that can achieve the best construction effect of deep foundation pits according to the differences in confined water layers and construction methods. Summary of the invention

[0003] In view of this, the purpose of this application is to provide a construction deformation prediction method, device, equipment and medium for deep foundation pit construction, which can determine the working conditions of each construction method in the target engineering area through the establishment of an orthogonal test scheme and a multivariate linear analysis method, and the relationship between the construction deformation at each stage of deep foundation pit construction and the distribution of the pressurized water layer in the target engineering area, so as to solve the problems existing in the prior art that the construction cost of deep foundation pit construction is high, the specific construction conditions are complex, and it is difficult to achieve a good deformation control effect, so as to achieve a good grasp of the deformation of foundation pit construction, and use this to guide the effect of optimizing the construction of deep foundation pit.

[0004] In the first aspect, an embodiment of the present application provides a method for predicting construction deformation of deep foundation pit construction, the method comprising: obtaining survey data and construction design data of a target engineering area; determining an orthogonal test scheme based on the distribution data of the pressurized water layer in the target engineering area; performing numerical simulation on the working conditions of each construction method in the construction design data to determine the deformation value under each working condition; performing multivariate linear analysis based on the orthogonal test scheme, the deformation value under the working condition of each construction method, and the distribution data of the pressurized water layer in the target engineering area to determine the relationship between the construction deformation of each construction method under the working condition at each stage of deep foundation pit construction in the target engineering area and the distribution of the pressurized water layer in the target engineering area.

[0005] Optionally, the steps of determining the orthogonal test scheme based on the distribution data of the confined water layer in the target engineering area include: determining the distribution of the confined water layer in the target engineering area based on the survey data of the target engineering area; determining the characteristic indicators of the double-layer confined water layer based on the distribution of the confined water layer in the target engineering area; determining the orthogonal test scheme based on the survey data of the target engineering area and the characteristic indicators of the double-layer confined water layer.

[0006] Optionally, the characteristic indicators of the double-layer confined water layer include: burial depth of the top of layer 1, thickness of layer 2, double-layer spacing, thickness of layer 2, pressure head of layer 1 and pressure head of layer 2.

[0007] Optionally, numerical simulation is performed on the working condition of each construction method in the construction design data to determine the deformation value under the working condition of each construction method: the material constitutive model is determined according to the characteristic indicators of the double-layer confined water layer; the working condition of the construction method is numerically simulated based on the material constitutive model to determine the data simulation analysis results, and the numerical simulation analysis results are used to indicate the deformation amount of the working condition of the construction method.

[0008] Optionally, the method further comprises: determining the anti-surge stability of the deep foundation pit according to the total soil pressure between the bottom of the foundation pit and the top of the confined water layer, the supporting force of the pressure head of the confined water layer in the initial state, the thickness of each layer of soil between the bottom of the foundation pit and the top of the confined water layer, the weight of each layer of soil between the bottom of the foundation pit and the top of the confined water layer, the height of the pressure head of the confined water layer, the standard bulk density of water, and the safety factor of the anti-surge stability of the bottom of the foundation pit

[0009] Optionally, the anti-surge stability of deep foundation pits is calculated by the following formula:

[0010] ,

[0011] in, is the total earth pressure between the bottom of the foundation pit and the top of the confined water layer, is the supporting force of the pressure head of the confined water layer in the initial state, It is the thickness of each layer of soil between the bottom of the foundation pit and the top of the confined water layer; It is the weight of each layer of soil between the bottom of the foundation pit and the top of the confined water layer; is the pressure head height of the confined water layer, is the standard bulk density of water, It is the safety factor of the foundation pit bottom against sudden surge.

[0012] Optionally, a multivariate linear analysis is performed according to the deformation values ​​under each working condition of the construction method and the distribution data of the confined water layer in the target engineering area through the following steps: a regression calculation model is determined according to the deformation values ​​under each working condition and the distribution data of the confined water layer in the target engineering area; the coefficients of the regression calculation model are estimated by multiple regression algorithms, and the regression fitting effects are compared, and the coefficients of the regression calculation model are determined by using the regression algorithm with the best regression fitting effect; based on the regression calculation model and the coefficients of the regression calculation model, the relationship between the construction deformation at each stage of deep foundation pit construction in the target engineering area under the working condition of each construction method and the distribution of the confined water layer in the target engineering area is determined.

[0013] In a second aspect, the embodiment of the present application further provides a construction deformation prediction device for deep foundation pit construction, the device comprising:

[0014] Data acquisition module, used to obtain survey data and construction design information of the target project area;

[0015] An orthogonal test scheme determination module is used to determine the orthogonal test scheme according to the confined water layer distribution data of the target project area;

[0016] The deformation value determination module is used to perform numerical simulation on the working condition of each construction method in the construction design data and determine the deformation value under each working condition;

[0017] The multivariate linear analysis module is used to perform multivariate linear analysis based on the orthogonal test scheme, the deformation value under the working condition of each construction method and the distribution data of the confined water layer in the target engineering area, so as to determine the relationship between the construction deformation at each stage of deep foundation pit construction in the target engineering area under the working condition of each construction method and the distribution data of the confined water layer in the target engineering area.

[0018] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory through the bus, and when the machine-readable instructions are executed by the processor, the steps of the construction deformation prediction method for deep foundation pit construction as described above are performed.

[0019] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the construction deformation prediction method for deep foundation pit construction as described above are executed.

[0020] The construction deformation prediction method, device, equipment and medium for deep foundation pit construction provided in the embodiments of the present application can determine the relationship between the construction deformation of each construction method in each stage of deep foundation pit construction in the target engineering area and the distribution of pressurized water layers in the target engineering area by establishing an orthogonal test scheme and a multivariate linear analysis method, so as to solve the problems existing in the prior art that the construction cost of deep foundation pit construction is high, the specific construction conditions are complicated, and it is difficult to achieve a good deformation control effect, so as to achieve the effect of having a good grasp of the deformation of foundation pit construction, and use this to guide the effect of optimizing the construction of deep foundation pit.

[0021] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A flowchart of a method for predicting construction deformation of a deep foundation pit provided in an embodiment of the present application;

[0024] Figure 2 A schematic diagram of the distribution of the confined water layer provided in the embodiment of the present application;

[0025] Figure 3 A comparison diagram of the maximum final deformation of the foundation pit provided in the embodiment of the present application;

[0026] Figure 4 A schematic diagram of the structure of a construction deformation prediction device for deep foundation pit construction provided in an embodiment of the present application;

[0027] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0029] First, the application scenarios to which this application is applicable are introduced. This application can be applied in the field of intelligent construction technology.

[0030] According to research, with the application and development of artificial intelligence technology in civil engineering construction, the current development of informatization and automation has made the construction of deep foundation pits gradually systematic and orderly; although mechanized construction is efficient, the construction cost is high, the specific construction conditions are complex, and it is difficult to achieve a good deformation control effect. The shift in construction focus has also become prominent, especially the grasp of the construction conditions of deep foundation pits in confined water strata is very important. Among them, the deformation of deep foundation pit construction in multi-layer confined water strata is mainly affected by factors such as stratum properties, confined water layer characteristics, and construction methods; in soft and water-rich strata, the distribution and pressure of confined water have a great influence on the structure of deep foundation pits.

[0031] Based on this, the embodiments of the present application provide a method, device, equipment and medium for predicting construction deformation of deep foundation pit construction, which can determine the relationship between the construction deformation of each construction method in each stage of deep foundation pit construction in the target engineering area and the distribution of pressurized water layers in the target engineering area by establishing an orthogonal test scheme and a multivariate linear analysis method, thereby solving the problems in the prior art that the construction cost of deep foundation pit construction is high, the specific construction conditions are complex, and it is difficult to achieve a good deformation control effect, thereby achieving a good grasp of the deformation of foundation pit construction, and using this to guide the effect of optimizing the construction of deep foundation pits.

[0032] See also Figure 1 , Figure 1 This is a flow chart of a method for predicting construction deformation of a deep foundation pit provided in an embodiment of the present application. Figure 1 As shown in , the construction deformation prediction method for deep foundation pit construction provided by the embodiment of the present application includes:

[0033] S101. Obtain survey data and construction design information for the target project area.

[0034] Here, while obtaining the survey data of the project area, the main distribution range of the regional confined water strata should be summarized to limit the impact of the differences in the distribution of confined water strata on the foundation pit construction process; the summary relies on the properties of the soil layers distributed in the project area, combined with the corresponding distribution of confined water layers, to determine the scope of discussion on the distribution of confined water layers under the overall analysis overview, and it is also necessary to grasp the overall design of the project and summarize the main processes and corresponding characteristics of the foundation pit construction methods.

[0035] Furthermore, the adopted construction method can be analyzed according to the specific situation, thereby highlighting the universality of this patent for the prediction of deformation of deep foundation pit construction. This patent can also be used to compare the deformation of foundation pit construction using different construction methods under the same pressurized water layer, and further understand the quantitative differences between different construction methods.

[0036] Among them, by summarizing the distribution of confined water layers, the quantitative relationship between foundation pit construction deformation and the characteristic indicators of double-layer confined water layers is discussed, and the influence of characteristic indicators of three or more layers of confined water layers can be analyzed, which shows the universality of this patent's method for analyzing the relationship between independent variables and dependent variables.

[0037] S102. Determine an orthogonal test plan based on the confined water layer distribution data of the target project area.

[0038] Specifically, according to the distribution data of the confined water layer in the target engineering area, the steps of determining the orthogonal test scheme include: determining the distribution of the confined water layer in the target engineering area according to the survey data of the target engineering area; determining the characteristic indicators of the double-layer confined water layer according to the distribution of the confined water layer in the target engineering area; determining the orthogonal test scheme according to the survey data of the target engineering area and the characteristic indicators of the double-layer confined water layer.

[0039] The characteristic indicators of the double-layer confined water layer include: the top burial depth of layer 1, the thickness of layer 2, the double-layer spacing, the thickness of layer 2, the pressure head of layer 1 and the pressure head of layer 2.

[0040] Optionally, the method further comprises: determining the anti-surge stability of the deep foundation pit according to the total soil pressure between the bottom of the foundation pit and the top of the confined water layer, the supporting force of the pressure head of the confined water layer in the initial state, the thickness of each layer of soil between the bottom of the foundation pit and the top of the confined water layer, the weight of each layer of soil between the bottom of the foundation pit and the top of the confined water layer, the height of the pressure head of the confined water layer, the standard bulk density of water, and the safety factor of the anti-surge stability of the bottom of the foundation pit

[0041] Specifically, the anti-surge stability of deep foundation pit can be calculated by the following formula:

[0042] ,

[0043] in, is the total earth pressure between the bottom of the foundation pit and the top of the confined water layer, is the supporting force of the pressure head of the confined water layer in the initial state, It is the thickness of each layer of soil between the bottom of the foundation pit and the top of the confined water layer; It is the weight of each layer of soil between the bottom of the foundation pit and the top of the confined water layer; is the pressure head height of the confined water layer, is the standard bulk density of water, It is the safety factor of the foundation pit bottom against sudden surge.

[0044] S103. Perform numerical simulation on the working condition of each construction method in the construction design data to determine the deformation value under each working condition.

[0045] Specifically, a numerical simulation is performed on the working condition of each construction method in the construction design data to determine the deformation value under the working condition of each construction method: the material constitutive model is determined according to the characteristic indicators of the double-layer confined water layer; the working condition of the construction method is numerically simulated based on the material constitutive model to determine the data simulation analysis result, and the numerical simulation analysis result is used to indicate the deformation amount of the working condition of the construction method.

[0046] Furthermore, the selected characteristic indicator factor level of the double-layer confined water layer is more conducive to determining the quantitative relationship between the foundation pit construction deformation and the characteristic indicator, and the obtained quantitative relationship has a smaller deviation, thereby obtaining a quantitative relationship that is more in line with the actual situation.

[0047] S104. Perform multivariate linear analysis based on the orthogonal test scheme, the deformation value under the working condition of each construction method and the distribution data of the confined water layer in the target engineering area to determine the relationship between the construction deformation of each construction method under the working condition of each stage of deep foundation pit construction in the target engineering area and the distribution of the confined water layer in the target engineering area.

[0048] Specifically, the following steps can be used to perform multivariate linear analysis based on the deformation values ​​under each working condition of the construction method and the distribution data of the confined water layer in the target engineering area: determine the regression calculation model based on the deformation values ​​under each working condition and the distribution data of the confined water layer in the target engineering area; estimate the coefficients of the regression calculation model through multiple regression algorithms, compare the regression fitting effects, and use the regression algorithm with the best regression fitting effect to determine the coefficients of the regression calculation model; determine the relationship between the construction deformation of each stage of deep foundation pit construction in the target engineering area under the working condition of each construction method and the distribution of the confined water layer in the target engineering area based on the regression calculation model and the coefficients of the regression calculation model.

[0049] Here, according to the principle of multiple linear regression method, the characteristics of the double-layer confined water layer under various working conditions obtained by numerical calculation are taken as independent variables, and the calculated value of the foundation pit construction deformation is taken as the dependent variable to obtain the regression calculation model.

[0050] Exemplarily, the regression calculation model may be:

[0051] ,

[0052] in: is the regression calculation value of the construction deformation k under the condition j of the double-layer confined water layer foundation pit;

[0053] , is the unknown coefficient in the multivariate linear regression formula; n is the characteristic number of the double-layer confined water layer; It represents the value of construction deformation k caused by characteristic i under working condition j of double-layer confined water layer foundation pit.

[0054] Among them, the regression calculation value of construction deformation k under the double-layer confined water layer foundation pit j condition can be calculated by the following formula:

[0055]

[0056] in, is the simulated value of construction deformation k under condition j of double-layer confined water layer foundation pit; is the error between the simulated value of the double-layer confined water layer foundation pit construction deformation and the regression calculated value, which obeys the normal distribution and is Independent of each other.

[0057] Here, in order to maximize the fitting degree of the multivariate linear regression curve and obtain the regression equation that best reflects the deformation of the foundation pit construction, it is necessary to make the total sum of squares of the variance between the measured data and the regression calculation data as small as possible while minimizing the regression sum of squares.

[0058] For example, assuming the number of field conditions is m, the following total deviation sum of squares can be obtained: , regression sum of squares and residual sum of squares The calculation formula is:

[0059]

[0060]

[0061]

[0062] Afterwards, you need to Find the partial derivative so that its partial derivative is zero and calculate the regression coefficient The normal equations for :

[0063]

[0064] Specifically, to determine the coefficients of the regression calculation model, the least squares method, ridge regression and lasso regression can be selected to estimate the coefficients of the regression equation, and the regression fitting effect can be compared. The main principles are shown in Table 1 below, where λ is a hyperparameter, which is a non-negative number; Ci is the coefficient of the regression equation, and in Lasso regression, coefficients with an absolute value less than λ / 2 will be forced to become zero.

[0065] Table 1:

[0066]

[0067] Optionally, in order to determine the regression effect of the regression equation on the foundation pit construction deformation, it is necessary to perform a significance test on it to determine whether the construction deformation regression calculation value as the dependent variable has a significant multivariate linear relationship with the characteristic index of the double-layer confined water layer under various working conditions. For the subsequent comparison of the construction deformation regression equation, the regression results using different coefficient estimation methods are compared in the results of the significance test of the fitting effect. The test method used is shown in Table 2 below.

[0068] Table 2:

[0069]

[0070] Among them, n is the number of sample groups substituted into the calculation of the multiple linear regression model; m is the number of independent variables in the multiple linear regression model. This paper selects 6 characteristic factors in total, so 6 is taken.

[0071] Specifying a significance level (Usually take ), when the obtained , it is believed that the multivariate linear regression fitting effect is significant, and there is a significant linear relationship between the dependent variable and the independent variable. See the table for details.

[0072] Specifically, based on the statistical results of numerical simulation of each working condition of the orthogonal test scheme, according to the principles of multivariate linear regression analysis and three coefficient estimation methods, Python code can be used for data training to obtain three sets of regression coefficients. Then, a set of coefficients with the best fitting effect and the strongest significance can be obtained through comparison. Then, the quantitative relationship between the construction deformation of the deep foundation pit at each stage under a certain construction method and the characteristic indicators of the double-layer confined water layer can be obtained.

[0073] It should be noted that the multivariate linear regression method used in this application is only the application method of this patent. More nonlinear regression analysis methods, support vector machines, neural networks and other machine learning methods can be used, which shows the diversity of this patent's quantitative relationship analysis method between deep foundation pit construction deformation and double-layer confined water layer characteristic indicators. Therefore, a reasonable quantitative relationship analysis method can be used for different geological strata, different construction methods and different confined water layer distributions.

[0074] Furthermore, the construction deformation prediction method of deep foundation pit construction, with the emphasis on the advancement of construction methods and the efficient and orderly construction process, the feasibility and universal applicability of the deformation prediction model for deep foundation pit construction in double-layer confined water strata based on orthogonal experiments and regression analysis methods can be intuitively perceived, and through more detailed and precise guidance on deformation prediction at each stage of construction, it has a good coordination effect on dynamic adjustment of construction in engineering applications and timely control of deformation, effectively reducing construction risks.

[0075] For example, the soil layer in Tianjin urban area is composed of interbedded soils deposited in marine and terrestrial phases, among which the Holocene phreatic aquifer includes phreatic water and micro-confined water, which can be roughly divided into a phreatic aquifer group and three micro-confined aquifer groups within a depth of 70 m. The general characteristics of each aquifer are shown in Table 3.

[0076] Table 3:

[0077]

[0078] Due to the large differences in the characteristics of each confined aquifer, the first and second confined aquifers are currently closely related to foundation pit excavation and precipitation, and the third and fourth confined aquifers have basically no impact on the foundation pit; the confined water is stored in silt and sand with a water level of 3 to 6 m; the first confined aquifer is 20 to 28 m deep, 4 to 8 m thick, and the upper waterproof top plate is 5 to 10 m thick, with no overflow recharge; the second confined aquifer is 35 to 45 m deep, 3 to 7 m thick, and the upper waterproof top plate is 14 to 20 m thick, with overflow recharge.

[0079] According to the hydrogeological conditions of the project, the situation of the confined water layer in the environment of the foundation pit of the project is relatively complex. There is a confined water layer within the excavation range of the foundation pit, and two confined water layers within the construction range of the ground-connected wall. The distribution depth of each confined water layer in the horizontal range fluctuates little. The specific situation of the confined water layer is as follows: Figure 2 as shown in .

[0080] The characteristic parameters of the on-site confined water layer are shown in Table 4 below:

[0081] Table 4:

[0082]

[0083] According to the actual on-site construction organization design data, the on-site construction design diagram is shown in Table 5 below, where “-” indicates the burial depth.

[0084] Table 5:

[0085]

[0086] According to the burial depth, thickness and pressure head of the first and second layers of confined water layers in Tianjin, relying on the actual engineering structure, according to the confined water layer conditions involved in the foundation pit in the engineering geological survey report, and on the premise of discussing the influence and change rules of each feature in a relatively uniform and dispersed manner, the levels of each factor are selected as shown in Table 6 below; the test index is the deformation of the foundation pit construction structure. For the three factors in this experimental design, each factor has five levels. This paper adopts the orthogonal test The orthogonal array of the experimental scheme is shown in Table 7 below.

[0087] Table 6:

[0088]

[0089] Table 7:

[0090]

[0091] According to the above-mentioned confined water layer safety analysis formula, the working conditions that require decompression and pressure reduction of the second confined water layer can be obtained as shown in Table 8 below, which includes the working conditions that require advance decompression and pressure reduction during foundation pit excavation. The decompression process is generally carried out one step before the final soil excavation.

[0092] Table 8:

[0093]

[0094] The foundation pit structure is designed for a subway foundation pit in Tianjin, where the excavation width is 25.9 m and the depth is 26.9 m. The numerical modeling rules are consistent with the single-layer confined water layer working condition. In order to simplify the model calculation, the model adopts a two-dimensional plane strain form, and the calculation size is set to x direction × y direction = 181 m × 81 m. The foundation pit excavation part is in the center of the model, the foundation pit boundary position is 77.4 m away from the left and right boundaries of the model, and the excavation pit bottom is 54.6 m away from the bottom boundary.

[0095] The model is divided into 2D rectangular units. The ground environment around the foundation pit is divided into grids by "regional mapping". The foundation pit structure is divided into grids by "automatic region". The outer contour of the tunnel is the main size control point. The vertical side length of the unit cell is 0.4 m, and the horizontal side length decreases from 2.0 m to 0.4 m inwards at an automatic gradient rate. The ground-connected wall is simulated by 2D units. In order to show the concrete self-waterproofing performance of the ground-connected wall, the structure is divided into 3 or more grids in the thickness direction. The temporary support and main structure constructed after the foundation pit excavation are simulated by 1D units. Because the construction feature of this project is the cover excavation method, the main structure inside the foundation pit will be alternately carried out with earth excavation and temporary support during construction, so the main structure is also considered in this model.

[0096] The model boundary uses the rapid stress boundary constraint method to set the displacement boundary conditions. According to the working conditions of different confined water layer water pressure discussed, the corresponding pressure head is applied to the model confined layer boundary. The foundation pit excavation is located in the middle of the model horizontally, excavated from the surface downward, and the construction process control is consistent with the site. The specific model is as follows Figure 2 , where h is the top burial depth of layer 1, M1 is the thickness of the first confined water layer, d is the double-layer spacing, and M2 is the thickness of the second confined water layer. The modeling sequence of numerical simulation is as follows: (1) Establishing the stratum model, assigning grid parameters, calculating the groundwater and stratum stress balance, and constructing the ground-connected wall, pillars and piles; (2) Excavation of foundation pit dewatering, construction of layer plates, and construction and removal of temporary support structures; (3) After excavation to the bottom of the foundation pit, constructing the foundation pit bottom plate.

[0097] Here, according to the relevant geological survey report and on-site inspection, the small strain hardening soil constitutive model is selected and the specific constitutive parameters used in the model are selected, as shown in Tables 9 and 10 below. Since the subway foundation pit of this project is basically in a water-rich area, and there are three underground confined water layers, the foundation pit retaining structure passes through two confined water layers, with thicknesses of 4 m and 13 m respectively. Therefore, in order to express the action form of the pressure head of the confined water layer, the interface unit is used to simulate the impermeable interface properties on both sides of the confined water layer; since only the influence of the confined water layer on the foundation pit structure in the silt sand and clay strata environment is explored, the physical and mechanical parameters of the model strata are consistent with the various soil layers on site. The design form and size parameters of the foundation pit structure are shown in Table 11 below, where the width of the rectangular component is represented by w, the height is represented by T, the diameter of the circular component is represented by d, and the thickness is represented by t.

[0098] Table 9:

[0099]

[0100] Table 10:

[0101]

[0102] Table 11:

[0103]

[0104] Afterwards, based on the above-mentioned design of the orthogonal test conditions, the Midas GTS NX numerical simulation software was used to calculate all 25 designed conditions. The calculation results of the foundation pit construction deformation are shown in Table 12 below, where A represents the top burial depth of layer 1, B represents the thickness of layer 1, C represents the double-layer spacing, D represents the thickness of layer 2, E represents the pressure head of layer 1, and F represents the pressure head of layer 2.

[0105] Table 12:

[0106]

[0107] Furthermore, according to the designed 25 double-layer confined water layer calculation conditions, the established two-dimensional stratum-structure model can be used to perform numerical simulation calculations respectively, and 25 sets of theoretical values ​​of foundation pit construction deformation under the designed working conditions can be obtained. In order to verify the reliability of the multiple linear regression equation calculated later for the prediction results of foundation pit construction deformation, 20% of the calculation data are retained and not involved in the regression fitting calculation. Based on the two-dimensional model calculation results under 25 groups of working conditions, the theoretical value of construction deformation calculated by the model is used as the regression target value, and the application of three linear regression coefficient estimation methods is implemented using Python language code. Three sets of multiple linear regression coefficients are obtained as shown in Table 13, and the multiple linear regression equations between foundation pit construction deformation and double-layer confined water layer characteristic factors are obtained. The significance test of the regression analysis results obtained by the three coefficient estimation methods is shown in Table 14 below, where MSE is the mean square error.

[0108] Table 13:

[0109]

[0110] Table 14:

[0111]

[0112] From Table 13 and Table 14, we can see that in the regression equation significance test results obtained by the three coefficient estimation methods, the multiple correlation coefficients are all close to 1.0, and the fitting effect is only achieved by the lasso estimation method at 0.8; according to the F test distribution table, ; Compared with the significance test results, under the condition of 95% confidence level, the dependent variable "regression calculation value of foundation pit ground-connected wall deflection" and the independent variable "characteristic value of double-layer confined water layer under various working conditions" only have significant linear relationship between the ols and lasso regression equations, and the fitting result of the ground-connected wall deflection regression equation is relatively reliable. From Durbin-Watson statistic = 0.592, it can be seen that there is obvious multicollinearity between the sample variables selected for regression analysis, because the characteristic factors of double-layer confined water layer need to conform to the conventional geological conditions on site and show mutual constraints. Among them, the significance test results of ols and lasso regression analysis are similar, and both are better than the ridge regression analysis test results.

[0113] Table 15:

[0114]

[0115] Table 16:

[0116]

[0117] It can be seen from Table 15 and Table 16 that in the regression equation significance test results obtained by the three coefficient estimation methods, the multiple correlation coefficients are all close to 1.0, and the lasso estimation method performs best in fitting effect; according to the F test distribution table, ; Compared with the significance test results, under the condition of 95% confidence level, the dependent variable "regression calculation value of foundation pit ground-connected wall deflection" and the independent variable "characteristic value of double-layer confined water layer under various working conditions" only have significant linear relationship in ols and lasso regression equations, and the fitting result of surface settlement regression equation is relatively reliable. From Durbin-Watson statistic = 0.945, it can be seen that there is obvious multicollinearity between the sample variables selected for regression analysis, because the characteristic factors of double-layer confined water layer must conform to the conventional geological conditions on site and show mutual constraints. Among them, the significance test results of ols and lasso regression analysis are good, and both are better than ridge regression analysis test results. Based on the above, considering the fitting effect of variables and the unbiased estimation of regression fitting values, the coefficient estimation of the regression equation for foundation pit construction deformation in subsequent cases is analyzed and verified by lasso regression method.

[0118] The quantitative relationship between the foundation pit construction deformation and the double-layer confined water layer characteristics was obtained by regression fitting of the simulation results of each working condition of the double-layer confined water layer orthogonal test. According to the characteristics of the double-layer confined water layer on site, the on-site theoretical deformation obtained by fitting the equation is shown in Table 17, and the comparison with the final deformation of the selected on-site monitoring section is as follows: Figure 3 shown.

[0119] Table 17:

[0120]

[0121] Depend on Figure 3 It can be seen that there is a gap between the theoretical results obtained by fitting and the actual monitoring deformation on site, but both are within the range of 0~5.0 mm. The only one with the largest difference is the construction deformation of Section 2. The large difference in performance may be mainly due to the fact that the numerical model established during the discussion of the orthogonal test conditions is itself a theoretical situation after simplifying the actual situation on site. There are also differences in the double-layer confined water layer between the models of various working conditions and the site. In addition, the average mean square error of the fitting regression equation obtained based on the orthogonal test results is also large, and there are also large differences in the stratum where the foundation pit is located and its surrounding environment, which leads to large deviations. Among them, the difference rates of the deformation monitoring values ​​with the three closest monitoring sections (Sections 1, 3, and 4) are about 7.1%, 12.9%, and 3.3% of the final deflection deviation of the ground-connected wall and about 15.1%, 16.9%, and 8.4% of the final surface settlement deviation, respectively. The fitting formula has a good prediction application effect. Considering the complexity and heterogeneity of the actual situation on site, the factors considered in the fitting formula still need to be improved, but the overall performance is good.

[0122] The method for predicting construction deformation of deep foundation pit construction provided in the embodiment of the present application can determine the relationship between the construction deformation of each construction method in each stage of deep foundation pit construction in the target engineering area and the distribution of pressurized water layers in the target engineering area by establishing an orthogonal test scheme and a multivariate linear analysis method, thereby solving the problems in the prior art of high construction cost of deep foundation pit construction, complex specific construction conditions, and difficulty in achieving good deformation control effects, thereby achieving a good grasp of the deformation of foundation pit construction and using this to guide the optimization construction of deep foundation pits.

[0123] Based on the same inventive concept, an embodiment of the present application also provides a construction deformation prediction device for deep foundation pit construction corresponding to the construction deformation prediction method for deep foundation pit construction. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the construction deformation prediction method for deep foundation pit construction in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0124] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of a construction deformation prediction device for deep foundation pit construction provided by an embodiment of the present application. Figure 4 As shown in , the construction deformation prediction device 400 for deep foundation pit construction includes:

[0125] Data acquisition module 401, used to acquire survey data and construction design information of the target project area;

[0126] An orthogonal test scheme determination module 402 is used to determine an orthogonal test scheme according to the confined water layer distribution data of the target project area;

[0127] The deformation value determination module 403 is used to perform numerical simulation on the working condition of each construction method in the construction design data to determine the deformation value under each working condition;

[0128] The multivariate linear analysis module 404 is used to perform multivariate linear analysis based on the orthogonal test scheme, the deformation value under the working condition of each construction method and the distribution data of the confined water layer in the target engineering area, so as to determine the relationship between the construction deformation at each stage of deep foundation pit construction in the target engineering area under the working condition of each construction method and the distribution data of the confined water layer in the target engineering area.

[0129] The construction deformation prediction device for deep foundation pit construction provided in the embodiment of the present application can determine the relationship between the construction deformation of each construction method in each stage of deep foundation pit construction in the target engineering area and the distribution of the pressurized water layer in the target engineering area by establishing an orthogonal test scheme and a multivariate linear analysis method, so as to solve the problems existing in the prior art that the construction cost of deep foundation pit construction is high, the specific construction conditions are complicated, and it is difficult to achieve a good deformation control effect, so as to achieve the effect of having a good grasp of the deformation of foundation pit construction, and use this to guide the effect of optimizing the construction of deep foundation pit.

[0130] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 5 As shown in , the electronic device 500 includes a processor 510 , a memory 520 and a bus 530 .

[0131] The memory 520 stores machine-readable instructions executable by the processor 510. When the electronic device 500 is running, the processor 510 communicates with the memory 520 via the bus 530. When the machine-readable instructions are executed by the processor 510, the above-mentioned Figure 1 The specific implementation of the steps of the method for predicting construction deformation of deep foundation pit construction in the method embodiment shown can be found in the method embodiment, which will not be repeated here.

[0132] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 The specific implementation of the steps of the method for predicting construction deformation of deep foundation pit construction in the method embodiment shown can be found in the method embodiment, which will not be repeated here.

[0133] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0134] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0136] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0137] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0138] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for predicting construction deformation of deep foundation pit construction, characterized in that: The method comprises: Obtain survey data and construction design information for the target project area; Determine the orthogonal test plan based on the confined water layer distribution data of the target project area; Conduct numerical simulation on the working conditions of each construction method in the construction design data to determine the deformation value under each working condition; A multivariate linear analysis is performed based on the orthogonal test scheme, the deformation value under the working condition of each construction method and the distribution data of the confined water layer in the target engineering area to determine the relationship between the construction deformation at each stage of deep foundation pit construction in the target engineering area under the working condition of each construction method and the distribution of the confined water layer in the target engineering area; Among them, the following steps are used to perform multivariate linear analysis based on the deformation value under each construction method and the distribution data of the confined water layer in the target project area: Determine the regression calculation model based on the deformation value under each working condition and the distribution data of the confined water layer in the target project area; The coefficients of the regression calculation model are estimated by using multiple regression algorithms, and the regression fitting effects are compared and selected, and the regression algorithm with the best regression fitting effect is used to determine the coefficients of the regression calculation model; According to the regression calculation model and its coefficients, the relationship between the construction deformation at each stage of deep foundation pit construction in the target engineering area and the distribution of the confined water layer in the target engineering area is determined.

2. The method according to claim 1, characterized in that According to the confined water layer distribution data of the target project area, the steps to determine the orthogonal test plan include: Determine the distribution of confined water layers in the target project area based on the survey data of the target project area; Determine the characteristic indicators of the double-layer confined water layer according to the distribution of the confined water layer in the target project area; The orthogonal test scheme is determined based on the survey data of the target engineering area and the characteristic indicators of the double-layer confined water layer.

3. The method according to claim 2, characterized in that The characteristic indicators of the double-layer confined water layer include: the top burial depth of layer 1, the thickness of layer 1, the double-layer spacing, the thickness of layer 2, the pressure head of layer 1 and the pressure head of layer 2.

4. The method according to claim 1, characterized in that: Perform numerical simulation on the working conditions of each construction method in the construction design data to determine the deformation value under the working conditions of each construction method: According to the characteristic indexes of the double-layer confined water layer, the material constitutive model is determined; The working condition of the construction method is numerically simulated based on the material constitutive model to determine the data simulation analysis result, and the numerical simulation analysis result is used to indicate the deformation amount of the working condition of the construction method.

5. The method according to claim 1, characterized in that The method further comprises: The anti-surge stability of deep foundation pit is determined based on the total soil pressure between the bottom of foundation pit and the top of confined water layer, the supporting force of the pressure head of confined water layer in the initial state, the thickness of each layer of soil between the bottom of foundation pit and the top of confined water layer, the weight of each layer of soil between the bottom of foundation pit and the top of confined water layer, the height of the pressure head of confined water layer, the standard bulk density of water and the safety factor of the anti-surge stability of the bottom of foundation pit.

6. The method according to claim 5, characterized in that The anti-surge stability of deep foundation pit is calculated by the following formula: in, is the total earth pressure between the bottom of the foundation pit and the top of the confined water layer, is the supporting force of the pressure head of the confined water layer in the initial state, It is the thickness of each layer of soil between the bottom of the foundation pit and the top of the confined water layer; It is the weight of each layer of soil between the bottom of the foundation pit and the top of the confined water layer; is the pressure head height of the confined water layer, is the standard bulk density of water, It is the safety factor of the foundation pit bottom against sudden surge.

7. A construction deformation prediction device for deep foundation pit construction, characterized in that: The device comprises: Data acquisition module, used to obtain survey data and construction design information of the target project area; An orthogonal test scheme determination module is used to determine the orthogonal test scheme according to the confined water layer distribution data of the target project area; The deformation value determination module is used to perform numerical simulation on the working condition of each construction method in the construction design data and determine the deformation value under each working condition; A multivariate linear analysis module is used to perform multivariate linear analysis based on the orthogonal test scheme, the deformation value under the working condition of each construction method and the distribution data of the confined water layer in the target engineering area, so as to determine the relationship between the construction deformation at each stage of deep foundation pit construction in the target engineering area under the working condition of each construction method and the distribution data of the confined water layer in the target engineering area; Among them, the multivariate linear analysis module is specifically used to determine the regression calculation model according to the deformation value under each working condition and the distribution data of the confined water layer in the target engineering area; the coefficients of the regression calculation model are estimated through multiple regression algorithms, and the regression fitting effects are compared, and the regression algorithm with the best regression fitting effect is used to determine the coefficients of the regression calculation model; based on the regression calculation model and the coefficients of the regression calculation model, the relationship between the construction deformation of each construction method in each stage of deep foundation pit construction in the target engineering area and the distribution of the confined water layer in the target engineering area is determined.

8. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of any method as claimed in claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are executed.

Images