Method for predicting fence lateral displacement and ground subsidence caused by foundation pit dewatering

Abstract

The invention relates to the technical field of foundation pit deformation prediction, and particularly discloses a method for predicting fence lateral displacement and land subsidence caused by foundation pit dewatering, and the method comprises the following steps: obtaining influence parameters of foundation pit deformation at a monitoring point, the influence parameters including the width of a foundation pit, the dewatering depth of the foundation pit and the supporting condition of an enclosure structure; calculating the maximum lateral displacement value of the deformation of the enclosure structure based on a pre-established maximum deformation model of the enclosure structure; and calculating a predicted value of the maximum settlement amount of the ground surface outside the foundation pit at the monitoring point, and predicting an actual value of the settlement amount of the ground surface outside the foundation pit at the monitoring point based on a pre-constructed neural network prediction model and an empirical formula. According to the method, a foundation pit periphery deformation prediction formula suitable for different working conditions is provided according to the change rule of the maximum settlement value and the actual settlement value of the retaining structure and the ground surface outside the foundation pit caused by rainfall before excavation, great convenience is provided for selection and optimization of foundation pit engineering design, and deformation control over foundation pit excavation is facilitated.

Description

Technical Field

[0001] The present invention specifically relates to the technical field of foundation pit deformation prediction, and in particular is a method for predicting lateral displacement of enclosures and ground settlement caused by foundation pit dewatering. Background Art

[0002] Most of the current research focuses on the impact of foundation pit excavation and precipitation on the lateral displacement of retaining structures and surrounding ground settlement, and a large number of literature has explored the deformation during foundation pit excavation and the impact of precipitation on foundation pit deformation. However, there are relatively few studies based on theoretical derivation, especially the impact of lateral displacement of retaining structures and deformation of surrounding strata caused by foundation pit excavation or precipitation. Literature shows that precipitation before foundation pit excavation may cause centimeter-level deformation of retaining structures and surrounding strata, which increases the potential risks in the construction process and may cause certain harm to the surrounding environment of the foundation pit and on-site construction personnel, thereby causing relatively serious economic losses.

[0003] At present, the technologies for predicting the deformation of surrounding strata caused by foundation pit excavation can be mainly divided into three categories: empirical formula, finite element method and theoretical method. For the empirical formula method, the existing problems are: poor adaptability to different soil conditions and construction conditions, low accuracy; less information can be provided, most of the existing empirical formulas only provide surface settlement envelopes, which are too conservative, and can not consider the relationship between support structure deformation and stratum settlement, so it cannot be well used for deformation control of foundation pit engineering. Summary of the invention

[0004] The purpose of the present invention is to provide a method for predicting lateral displacement of enclosures and ground settlement caused by foundation pit dewatering, so as to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for predicting lateral displacement of enclosure caused by foundation pit dewatering, comprising the following steps:

[0007] Obtaining influencing parameters of foundation pit deformation at the monitoring point, wherein the influencing parameters include foundation pit width, foundation pit dewatering depth, and support conditions of the surrounding structure;

[0008] The maximum lateral displacement value of the enclosure structure deformation is calculated based on the pre-established maximum enclosure structure deformation model, wherein the maximum enclosure structure deformation model includes the maximum enclosure structure deformation model I based on the case where there is no first support on the top of the enclosure structure wall and the maximum enclosure structure deformation model II based on the case where there is a first support on the top of the enclosure structure wall.

[0009] As a further solution of the present invention: the deformation of the foundation pit includes the lateral displacement of the retaining structure and the surface settlement outside the foundation pit, and the support conditions of the retaining structure include the first support arranged on the top of the retaining structure wall and the first support not arranged on the top of the retaining structure wall.

[0010] As a further solution of the present invention: the foundation pit includes a narrow strip foundation pit and a wide width foundation pit, the width of the narrow strip foundation pit is less than or equal to 60m, the width of the wide width foundation pit is greater than 60m, the narrow strip foundation pit adopts a combination of braces and angle braces to set the first support, and the wide width foundation pit adopts a simplified support setting method.

[0011] As a further solution of the present invention: Model I of the maximum deformation of the enclosure structure based on the absence of the first support on the top of the enclosure structure wall is:

[0012] Maximum lateral displacement of the retaining structure δ hm The regression relationship function expression between the width of the foundation pit b is:

[0013]

[0014] Where: k2=-1.2991H d +44.97, t' h =-1.42H d +49.9, H d Indicates the depth of foundation pit dewatering;

[0015] Model II of the maximum deformation of the enclosure structure based on the first support on the top of the enclosure structure wall is:

[0016] Maximum lateral displacement of the retaining structure δ' hm The regression relationship function expression between the width of the foundation pit b is:

[0017]

[0018] Where: k4 = -2.29H d +24.6, t' k =-0.682H d +22.8, H d Indicates the depth of foundation pit dewatering.

[0019] As a further solution of the present invention: the empirical formula is: the regression relationship function expression between the maximum surface settlement outside the foundation pit and the maximum lateral displacement value of the deformation of the retaining structure:

[0020]

[0021] Where: S represents the first predicted value of the surface settlement outside the foundation pit, S vm =αS hm ; d represents the distance from the excavation point to the center of the foundation pit; H represents the excavation depth of the foundation pit; S vm Represents the predicted value of the maximum surface settlement outside the foundation pit; S hm Indicates the maximum lateral displacement of the deformation of the enclosure structure. In the case where there is no first support on the top of the enclosure structure wall, S hm =δ hm , when there is the first support on the top of the retaining structure wall, S hm =δ′ hm ; α is the empirical coefficient, generally taken as 1.0; is the proportionality coefficient, generally taken as 0.4%.

[0022] A method for predicting ground settlement caused by foundation pit dewatering, comprising calculating the maximum lateral displacement value of the deformation of the retaining structure according to the above-mentioned method for predicting lateral displacement of retaining structures caused by foundation pit dewatering, and further comprising the following steps:

[0023] Calculate the predicted value of the maximum surface settlement outside the foundation pit at the monitoring point;

[0024] The actual value of the surface settlement outside the foundation pit at the monitoring point is predicted based on the pre-built neural network prediction model and the empirical formula. The method for predicting the actual value of the surface settlement outside the foundation pit at the monitoring point based on the pre-built neural network prediction model and the empirical formula is as follows:

[0025] Step 1: Calculate the first predicted value of the surface settlement outside the foundation pit based on the empirical formula;

[0026] Step 2: Calculate the second predicted value of the surface settlement outside the foundation pit based on the pre-built neural network prediction model.

[0027] Step 3: Take the average of the first predicted value and the second predicted value as the actual value of the surface settlement outside the foundation pit at the monitoring point.

[0028] As a further solution of the present invention: a method for constructing a neural network prediction model comprises the following steps:

[0029] Obtain historical data of maximum predicted value of foundation pit deformation and actual value of foundation pit deformation at monitoring points as sample data;

[0030] Determine the neural network structure parameters, including the number of neurons in the input layer, hidden layer, and output layer.

[0031] The weights and thresholds of the neural network are cascaded in sequence, including the input hidden layer weights, hidden thresholds, hidden output layer weights, and output thresholds; the population size is set, the weights and thresholds of the neural network are encoded, and the initial population is generated; the fitness function is determined, and the error between the expected output value and the network output value is used as the evaluation criterion;

[0032] The selection process determines the probability of an individual being selected to enter the next generation based on the fitness of the individual in the population;

[0033] In the crossover process, according to the crossover probability, the crossover individuals and crossover positions are randomly selected to form new individuals;

[0034] In the mutation process, according to the mutation probability, the mutation individuals and mutation positions are randomly selected to form new individuals;

[0035] The neural network performs forward propagation, calculates the global error, adjusts the network parameters, including weights and thresholds, and repeats the learning and training. When the required accuracy is achieved or the upper limit of the learning times is reached, the network training is terminated to obtain the neural network prediction model.

[0036] As a further solution of the present invention: the fitness function is:

[0037]

[0038] Where: N is the number of samples, T i is the actual value, and T0 is the predicted value.

[0039] As a further solution of the present invention: the forward propagation function is:

[0040]

[0041] Where: f(x) is the activation function, is the output value, k is the number of layers, and j is the number of nodes.

[0042] As a further solution of the present invention: the probability is calculated as follows:

[0043]

[0044] Where: s is the probability, q is the population fitness, and n is the population size.

[0045] As a further solution of the present invention: the calculation method of the predicted value of the maximum surface settlement outside the foundation pit at the monitoring point includes the following two methods:

[0046] Method 1: For the same foundation pit width and different precipitation depths, the predicted value of the maximum surface settlement outside the foundation pit δ vm With different precipitation depth H dThe regression relationship function expression between:

[0047]

[0048] Where: t v =-0.95H d +34.50,y v =0.15e 2 +2;

[0049] Method 2: For the same precipitation depth and different foundation pit widths, the predicted value of the maximum surface settlement outside the foundation pit is δ' vm The regression relationship function expression between different foundation pit widths b:

[0050]

[0051] Where: A' v =-0.275H d +1.98, t' v =2.05e 2.95 +4.5, y' v =0.018e 2.75 +0.09.

[0052] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention proposes a deformation prediction formula for the periphery of the foundation pit applicable to different working conditions through the changing law of the maximum and actual settlement values ​​of the retaining structure and the surface outside the foundation pit caused by precipitation before excavation, which provides great convenience for the selection and optimization of the foundation pit engineering design, is beneficial to the deformation control of the foundation pit excavation, and has a good value for promotion and application. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 Flow chart of the method for predicting ground subsidence caused by foundation pit dewatering.

[0054] Figure 2 The flowchart is a method for constructing a neural network prediction model in the method for predicting ground subsidence caused by foundation pit dewatering.

[0055] Figure 3 The present invention is a flow chart of a method for predicting the actual value of the surface settlement outside the foundation pit at the monitoring point based on a pre-built neural network prediction model and an empirical formula in the ground settlement prediction method caused by foundation pit dewatering. DETAILED DESCRIPTION

[0056] Below, the present application is further described in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form a new embodiment.

[0057] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in combination with specific embodiments and with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are intended to distinguish two non-identical entities or non-identical parameters with the same name. It can be seen that "first" and "second" are only for the convenience of expression and should not be understood as limitations on the embodiments of the present invention. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, other steps or units inherent to a process, method, system, product or device that includes a series of steps or units.

[0059] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0060] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0061] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0062] Based on this, the current technologies for predicting deformation of surrounding strata caused by foundation pit excavation can be mainly divided into three categories: empirical formula, finite element method and theoretical method. For the empirical formula method, the problems existing in the existing technology are: poor adaptability to different soil conditions and construction conditions, low accuracy; less information can be provided, most of the existing empirical formulas only provide surface settlement envelopes, which are too conservative, and also fail to consider the relationship between support structure deformation and stratum settlement, so they cannot be well applied to deformation control of foundation pit engineering.

[0063] See also Figure 1-Figure 3 In an embodiment of the present invention, a method for predicting ground subsidence caused by foundation pit dewatering comprises the following steps:

[0064] S101, obtaining influencing parameters of foundation pit deformation at the monitoring point, wherein the influencing parameters include foundation pit width, foundation pit dewatering depth, and support conditions of the retaining structure, wherein the foundation pit deformation includes lateral displacement of the retaining structure and surface settlement outside the foundation pit, and the support conditions of the retaining structure include whether the first support is arranged on the top of the retaining structure wall or not, and the first support mainly functions to limit deformation of the top of the wall;

[0065] In step S101 of the embodiment of the present application, since the width of the foundation pit varies in a large range, the embodiment divides the foundation pit into a narrow strip foundation pit and a wide width foundation pit according to the size of the foundation pit width. The width of the narrow strip foundation pit is less than or equal to 60m, and the specific foundation pit width is 20m, 30m or 40m, etc. The width of the wide width foundation pit is greater than 60m, and the specific foundation pit width is 80m, 120m, 160m or 200m, etc. For the narrow strip foundation pit, the first support is set by combining the brace and the angle brace. For the wide width foundation pit, a simplified support setting method is adopted, that is, part of the support is cut off and a fixed end is set at the end point. For the two different support setting methods, the support materials are all set to reinforced concrete support with a cross-sectional size of 800mm*800mm, using B31 beam elements, Young's modulus set to 30GPa, and Poisson's ratio set to 0.2; it should be noted that the use of a brace arrangement for large-width foundation pits will increase the slenderness ratio of the support structure, thereby reducing the support effect. In actual projects, when setting support schemes for large-width foundation pits, ring braces, a combination of braces and angle braces, or trusses are generally used.

[0066] S102, calculating the maximum lateral displacement value of the enclosure structure deformation based on a pre-established enclosure structure deformation maximum value model, wherein the enclosure structure deformation maximum value model includes an enclosure structure deformation maximum value model I based on a case where there is no first support on the enclosure structure wall top and an enclosure structure deformation maximum value model II based on a case where there is a first support on the enclosure structure wall top;

[0067] In step S102 of the embodiment of the present application, the maximum deformation model I of the enclosure structure based on the absence of the first support on the top of the enclosure structure wall is:

[0068] Maximum lateral displacement of the retaining structure δ hm The regression relationship function expression between the width of the foundation pit b is:

[0069]

[0070] Where: k2=-1.2991H d +44.97, t' h =-1.42H d +49.9, H d Indicates the depth of foundation pit dewatering;

[0071] Model II of the maximum deformation of the enclosure structure based on the first support on the top of the enclosure structure wall is:

[0072] Maximum lateral displacement of the retaining structure δ' hm The regression relationship function expression between the width of the foundation pit b is:

[0073]

[0074] Where: k4 = -2.29H d +24.6, t' k =-0.682H d +22.8, H d Indicates the depth of foundation pit dewatering.

[0075] S103, calculating the predicted value of the maximum surface settlement outside the foundation pit at the monitoring point, and predicting the actual value of the surface settlement outside the foundation pit at the monitoring point based on the pre-built neural network prediction model and the empirical formula, wherein the method for predicting the actual value of the surface settlement outside the foundation pit at the monitoring point based on the pre-built neural network prediction model and the empirical formula is:

[0076] Step 1: Calculate the first predicted value of the surface settlement outside the foundation pit based on the empirical formula;

[0077] Step 2: Calculate the second predicted value of the surface settlement outside the foundation pit based on the pre-built neural network prediction model.

[0078] Step 3: Take the average of the first predicted value and the second predicted value as the actual value of the surface settlement outside the foundation pit at the monitoring point.

[0079] Further, in the embodiment of the present application, the empirical formula is: the regression relationship function expression between the maximum surface settlement outside the foundation pit and the maximum lateral displacement value of the deformation of the retaining structure:

[0080]

[0081] Where: S represents the first predicted value of the surface settlement outside the foundation pit, S vm =αS hm ; d represents the distance from the excavation point to the center of the foundation pit; H represents the excavation depth of the foundation pit; S vm Represents the predicted value of the maximum surface settlement outside the foundation pit; S hm Indicates the maximum lateral displacement of the deformation of the enclosure structure. In the case where there is no first support on the top of the enclosure structure wall, S hm =δ hm, when there is the first support on the top of the retaining structure wall, S hm =δ′ hm ; α is the empirical coefficient, generally taken as 1.0; is the proportionality coefficient, generally taken as 0.4%.

[0082] In step 103 of the embodiment of the present application, the method for constructing a neural network prediction model includes the following steps:

[0083] S201, obtaining historical data of the predicted value of the maximum surface settlement outside the foundation pit and the actual value of the surface settlement outside the foundation pit at the monitoring point as sample data;

[0084] S202, determine the neural network structure parameters, including the number of neurons in the input layer, hidden layer and output layer. During training, first map the sample data to the hidden layer, and then map it to the output layer through the hidden layer. Compare the output result with the actual value, and then backpropagate the difference between the two. Repeat the calculation until the end. For different tasks, the number of input layers, hidden layers and output layers of the neural network can be expanded or reduced according to training needs to improve the adaptability of the network.

[0085] S203, cascading the weights and thresholds of the neural network in order, including input hidden layer weights, hidden thresholds, hidden output layer weights, and output thresholds; setting the population size, encoding the weights and thresholds of the neural network, and generating an initial population; determining the fitness function, using the error between the expected output value and the network output value as the criterion, the fitness function is used to evaluate the quality of individuals in the model, and each individual in the algorithm represents a set of weights and biases; in the embodiment of the present invention, the fitness function is:

[0086]

[0087] Where: N is the number of samples, T i is the actual value, and T0 is the predicted value.

[0088] S204, the selection process, according to the fitness of individuals in the population, determines the probability of individuals being selected to enter the next generation, wherein the probability is calculated as follows:

[0089]

[0090] Where: s is the probability, q is the population fitness, and n is the population size.

[0091] In the crossover process, according to the crossover probability, the crossover individuals and crossover positions are randomly selected to form new individuals;

[0092] In the mutation process, according to the mutation probability, the mutation individuals and mutation positions are randomly selected to form new individuals;

[0093] S205, the neural network performs forward propagation, calculates the global error, adjusts the parameters of the network, including weights and thresholds, and repeats the learning and training. When the required accuracy is achieved or the upper limit of the learning times is reached, the network training is terminated to obtain the neural network prediction model. In the embodiment of the present application, the forward propagation function is:

[0094]

[0095] Where: f(x) is the activation function, is the output value, k is the number of layers, and j is the number of nodes.

[0096] Furthermore, in step 103 of the embodiment of the present application, the method for calculating the predicted value of the maximum surface settlement outside the foundation pit at the monitoring point includes the following two methods:

[0097] Method 1: For the same foundation pit width and different precipitation depths, the predicted value of the maximum surface settlement outside the foundation pit δ vm With different precipitation depth H d The regression relationship function expression between:

[0098]

[0099] Where: t v =-0.95H d +34.50,y v =0.15e 2 +2;

[0100] Method 2: For the same precipitation depth and different foundation pit widths, the predicted value of the maximum surface settlement outside the foundation pit is δ' vm The regression relationship function expression between different foundation pit widths b:

[0101]

[0102] Where: A' v =-0.275H d +1.98, t' v =2.05e 2.95 +4.5, y' v =0.018e 2.75 +0.09.

[0103] In summary, the present invention proposes a deformation prediction formula for the perimeter of the foundation pit that is suitable for different working conditions through the changing law of the maximum and actual settlement values ​​of the retaining structure and the surface outside the foundation pit caused by precipitation before excavation. It provides great convenience for the selection and optimization of the foundation pit engineering design, is beneficial to the deformation control of the foundation pit excavation, and has a good value for promotion and application.

[0104] It will also be appreciated by those skilled in the art that various exemplary logic blocks, modules, circuits and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, a general description has been given to the functions of various schematic components, blocks, modules, circuits and steps. Whether this function is implemented as software or hardware depends on specific applications and the design constraints imposed on the entire system. Those skilled in the art can implement the function in various ways for each specific application, but this implementation decision should not be interpreted as causing a departure from the disclosed scope of the embodiments of the present invention.

[0105] Finally, it should be noted that the computer-readable storage medium (e.g., memory) herein may be a volatile memory or a nonvolatile memory, or may include both a volatile memory and a nonvolatile memory. As an example and not by way of limitation, a nonvolatile memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. A volatile memory may include a random access memory (RAM), which may act as an external cache memory. As an example and not by way of limitation, RAM may be obtained in a variety of forms, such as synchronous RAM (DRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The storage devices of the disclosed aspects are intended to include, but are not limited to, these and other suitable types of memory.

[0106] The various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure herein may be implemented or executed using the following components designed to perform the functions herein: a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination of these components. A general purpose processor may be a microprocessor, but alternatively, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP, and / or any other such configuration.

[0107] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0108] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A method for predicting lateral displacement of enclosure caused by foundation pit dewatering, characterized in that: The following steps are involved: Obtaining influencing parameters of foundation pit deformation at the monitoring point, wherein the influencing parameters include foundation pit width, foundation pit dewatering depth, and support conditions of the surrounding structure; The maximum lateral displacement value of the retaining structure deformation is calculated based on the pre-established maximum deformation model of the retaining structure.

2. The method for predicting lateral displacement of enclosure caused by foundation pit dewatering according to claim 1 is characterized in that: The deformation of the foundation pit includes the lateral displacement of the retaining structure and the surface settlement outside the foundation pit. The support conditions of the retaining structure include whether the first support is arranged on the top of the retaining structure wall or not.

3. The method for predicting lateral displacement of enclosure caused by foundation pit dewatering according to claim 2 is characterized in that: The foundation pit includes a narrow strip foundation pit and a wide width foundation pit. The width of the narrow strip foundation pit is less than or equal to 60m, and the width of the wide width foundation pit is greater than 60m. The narrow strip foundation pit adopts a combination of braces and angle braces to set the first support, and the wide width foundation pit adopts a simplified support setting method.

4. The method for predicting lateral displacement of enclosure caused by foundation pit dewatering according to claim 1 is characterized in that: The maximum deformation model of the enclosure structure includes the maximum deformation model I of the enclosure structure based on the case where there is no first support on the top of the enclosure structure wall and the maximum deformation model II of the enclosure structure based on the case where there is the first support on the top of the enclosure structure wall.

5. A method for predicting ground settlement caused by foundation pit dewatering, comprising calculating the maximum lateral displacement value of the deformation of the retaining structure according to the method for predicting lateral displacement of retaining structures caused by foundation pit dewatering according to any one of claims 1 to 4, characterized in that: The following steps are also included: Calculate the predicted value of the maximum surface settlement outside the foundation pit at the monitoring point; The actual value of the surface settlement outside the foundation pit at the monitoring point is predicted based on the pre-built neural network prediction model and empirical formula.

6. The method for predicting ground subsidence caused by foundation pit dewatering according to claim 5, characterized in that: The method for constructing a neural network prediction model includes the following steps: Obtain historical data of maximum predicted value of foundation pit deformation and actual value of foundation pit deformation at monitoring points as sample data; Determine the neural network structure parameters, including the number of neurons in the input layer, hidden layer, and output layer. The weights and thresholds of the neural network are cascaded in sequence, including the input hidden layer weights, hidden thresholds, hidden output layer weights, and output thresholds; the population size is set, the weights and thresholds of the neural network are encoded, and the initial population is generated; the fitness function is determined, and the error between the expected output value and the network output value is used as the evaluation criterion; The selection process determines the probability of an individual being selected to enter the next generation based on the fitness of the individual in the population; In the crossover process, according to the crossover probability, the crossover individuals and crossover positions are randomly selected to form new individuals; In the mutation process, according to the mutation probability, the mutation individuals and mutation positions are randomly selected to form new individuals; The neural network performs forward propagation, calculates the global error, adjusts the network parameters, including weights and thresholds, and repeats the learning and training. When the required accuracy is achieved or the upper limit of the learning times is reached, the network training is terminated to obtain the neural network prediction model.

7. The method for predicting ground subsidence caused by foundation pit dewatering according to claim 6, characterized in that: The method for predicting the actual value of the surface settlement outside the foundation pit at the monitoring point based on the pre-built neural network prediction model and the empirical formula includes the following steps: Calculate the first predicted value of the surface settlement outside the foundation pit based on the empirical formula; The second predicted value of the surface settlement outside the foundation pit is calculated based on the pre-built neural network prediction model. The average of the first predicted value and the second predicted value is taken as the actual value of the surface settlement outside the foundation pit at the monitoring point.

8. The method for predicting ground subsidence caused by foundation pit dewatering according to claim 7, characterized in that: The empirical formula is: Where: S represents the first predicted value of the surface settlement outside the foundation pit, S vm =αS hm ; d represents the distance from the excavation point to the center of the foundation pit; H represents the excavation depth of the foundation pit; S vm Represents the predicted value of the maximum surface settlement outside the foundation pit; S hm Indicates the maximum lateral displacement value of the deformation of the enclosure structure.

9. The method for predicting ground subsidence caused by foundation pit dewatering according to claim 8, characterized in that: In the case of no first support on the top of the enclosure wall, S hm =δ hm , when there is the first support on the top of the retaining structure wall, S hm =δ h ' m .

10. The method for predicting ground subsidence caused by foundation pit dewatering according to claim 9, characterized in that: The calculation method of the predicted value of the maximum surface settlement outside the foundation pit at the monitoring point includes the case where the foundation pit width is the same but the precipitation depth is different, and the case where the precipitation depth is the same but the foundation pit width is different.

Images