Method and system for simulating horizontal deformation of subway structure in subway double-sided extension

Abstract

The present invention relates to the technical field of numerical simulation and neural network, and specifically discloses a method and system for simulating horizontal deformation of a subway structure for two-sided extension of a subway. The method comprises the following steps: dividing a soil body to be excavated around a subway station into a plurality of plots to be excavated; simulating excavation of the plots to be excavated by numerical simulation, and calculating the horizontal deformation of the subway station; determining an excavation rate of the plots to be excavated according to the horizontal deformation corresponding to a single simulated excavation; generating a horizontal deformation for the subway station by a neural network model; determining an excavation process set in which the horizontal deformation of the subway station is less than a preset value by the prediction model; eliminating erroneous excavation processes in the excavation process set by empirical data and construction standards; and determining an optimal excavation process with the shortest construction period in the eliminated excavation process set; and being able to effectively reduce the deformation influence of the foundation pit excavation around the subway station on the subway station while ensuring the construction period.

Description

Technical Field

[0001] The present invention relates to the field of numerical simulation and neural network technology, and in particular to a method and system for simulating horizontal deformation of a subway structure for double-sided extension of a subway. Background Art

[0002] During the urban construction process, the construction around subway stations has a great impact on the stratum stability of subway stations, especially those in soft soil areas. During the construction of underground structures such as foundation pit excavation, the unloading effect of the surrounding soil will cause the foundation pit to deform to a certain extent, causing the adjacent buildings (such as tunnels) to deform accordingly along with the soil, thus endangering safety. Therefore, the traditional construction method of buildings around subway stations usually adopts a segmented and block excavation method, which will cause deformation of the subway station soil, especially horizontal deformation. If this horizontal deformation cannot be effectively controlled, it may cause the settlement and tilt of the subway station soil, and even affect the overall stability of the subway station. Therefore, in order to reduce the impact of underground construction on surrounding buildings and protect the overall stability and safety of underground structures, it is necessary to predict and control the deformation of underground structures.

[0003] In the prior art, some methods predict and control stratum deformation by introducing numerical simulation. For example, a neural network is used to take the geotechnical parameters of existing subways as input values, and the ground settlement at the detection point is used as the output value for training at different horizontal distances between the excavation face and the monitoring point. The trained model is used to analyze the ground settlement above other subways that are about to be constructed. It mainly includes relevant data preparation, simulation process prediction results and accuracy verification. It can accurately predict the ground settlement at the detection point based on the existing geotechnical parameters of various subways, and provide a measurement basis for the safety of ground buildings and the prevention of abnormal settlement. However, these methods usually rely on a large amount of on-site monitoring data and complex calculation models, and have low calculation accuracy and efficiency. In addition, the control and optimization of the excavation rate are often ignored in the prior art, resulting in the inability to flexibly adjust the excavation strategy according to the real-time changes of the stratum during the actual construction process, thereby increasing the construction risk and engineering cost.

[0004] In addition, although neural network models are used in some scenarios to predict and control the deformation of the strata during construction, due to the small amount of sample data and uneven distribution of samples, the existing neural network models often show poor generalization ability when processing small sample data and cannot accurately predict the deformation of the strata under different processes. This makes the existing technology obviously insufficient in controlling complex strata deformation.

[0005] Therefore, there is an urgent need for a method that can combine numerical simulation and neural network models to not only improve the accuracy of predicting stratum deformation, but also optimize the excavation process and reduce horizontal deformation, thereby ensuring the safety and efficiency of the construction process. Summary of the invention

[0006] The purpose of the present invention is to provide a method and system for simulating horizontal deformation of subway structures for subway double-sided extension, which can combine the methods of numerical simulation and neural network model, so as to improve the accuracy of predicting stratum deformation, optimize the excavation process, reduce horizontal deformation, and thus ensure the safety and efficiency of the construction process.

[0007] On the one hand, the present invention provides a method for simulating horizontal deformation of a subway structure for a subway double-sided extension, the method comprising dividing the soil to be excavated around the subway station into a plurality of plots to be excavated in the horizontal and vertical directions;

[0008] Through numerical simulation, the proposed excavation site is simulated and the horizontal deformation of the subway station after a single simulated excavation is calculated;

[0009] Determine the excavation rate of the corresponding plot to be excavated according to the horizontal deformation corresponding to a single simulated excavation;

[0010] The relationship between the excavation process and the horizontal deformation of the subway station is trained through a neural network model to obtain a prediction model to generate the horizontal deformation of the subway station corresponding to the excavation process;

[0011] Determine, by the prediction model, a set of excavation procedures in which the horizontal deformation of the subway station is less than a preset value;

[0012] Eliminate incorrect excavation procedures in the excavation procedure set by using empirical data and construction standards;

[0013] In the set of excavation procedures that have been eliminated, the optimal excavation procedure with the shortest construction period is determined according to the excavation rate of each simulated excavation.

[0014] As a preferred technical solution for the method of simulating horizontal deformation of subway structures for subway double-sided extension, the method of determining the excavation rate of the corresponding plot to be excavated according to the horizontal deformation amount corresponding to a single simulated excavation includes: comparing the horizontal deformation amount with a first deformation threshold value, and if the horizontal deformation amount is less than the first deformation threshold value, determining that the corresponding simulated excavation is carried out at a standard excavation rate.

[0015] As a preferred technical solution of the method for simulating horizontal deformation of subway structure for two-sided extension of subway, the method of determining the excavation rate of the corresponding plot to be excavated according to the horizontal deformation amount corresponding to a single simulated excavation further includes, if the horizontal deformation amount is greater than or equal to the first deformation threshold, executing the following steps:

[0016] Divide the land to be excavated into several layers;

[0017] Simulate excavation for each layer in turn at the standard excavation rate;

[0018] Determine the fault layer in which the horizontal deformation of the subway station in the simulated excavation of each layer is greater than a second deformation threshold;

[0019] excavating the fault layer at an excavation rate that decreases step by step from the standard excavation rate until the horizontal deformation of the layer is less than the second deformation threshold or reaches the minimum excavation rate, and determining the excavation rate that meets the corresponding conditions as the layer excavation rate;

[0020] Calculate the excavation rate of the proposed excavation plot according to the determined excavation rates of each layer;

[0021] The second deformation threshold is determined according to the first deformation threshold and the number of layers of the planned excavation plot.

[0022] As a preferred technical solution for simulating the horizontal deformation of subway structures for subway double-sided extension, the method of simulating excavation of the proposed excavation plot through numerical simulation and calculating the horizontal deformation of the subway station after a single simulated excavation includes:

[0023] Before simulating excavation, input geological parameters related to the proposed excavation site and the subway station;

[0024] The horizontal deformation of the subway station during the excavation process is calculated through finite element analysis.

[0025] As a preferred technical solution for simulating the horizontal deformation of subway structures in subway double-sided extension, the relationship between the excavation process and the horizontal deformation of the subway station is trained by a neural network model to generate the horizontal deformation of the subway station corresponding to the excavation process, including:

[0026] Get a simulated data set;

[0027] Preprocessing the simulated data set to remove noise data and outliers;

[0028] Normalizing the simulated data set;

[0029] The normalized simulated data set is divided into a training set and a validation set, where the training set is used to train the neural network model and the validation set is used to evaluate the model performance;

[0030] Constructing a neural network model, the model comprising an input layer, a plurality of hidden layers and an output layer, the input layer receiving relevant parameters of the excavation process, and the output layer generating horizontal deformation of the subway station;

[0031] The simulation data set includes the location of a single simulated excavation, the horizontal deformation of the subway station corresponding to the single simulated excavation, the simulated excavation process, and the horizontal deformation of the subway station after executing the simulated excavation process.

[0032] As a preferred technical solution for the method of simulating the horizontal deformation of subway structures for subway double-sided extension, the optimal excavation process with the shortest construction period determined according to the excavation rate of each simulated excavation includes:

[0033] Statistically calculate the excavation rate corresponding to each simulated excavation in the excavation process;

[0034] The excavation rate of each simulated excavation is integrated and calculated to obtain the construction time of each excavation process;

[0035] The construction times are compared and the excavation process with the shortest construction time is determined as the optimal excavation process.

[0036] As a preferred technical solution for the method of simulating the horizontal deformation of subway structures for subway double-sided extension, the initial number of plots to be excavated corresponding to a single simulated excavation is three, and the simulated excavation of the plots to be excavated by numerical simulation and the calculation of the horizontal deformation of the subway station after the single simulated excavation also include:

[0037] The simulated excavation is performed with the initial quantity, and the horizontal deformation of the subway station is compared with the first deformation threshold. If the horizontal deformation of the subway station is less than the first preset threshold, the data of the simulated excavation is input into the prediction model.

[0038] As a preferred technical solution of the method for simulating horizontal deformation of subway structure for two-sided subway expansion, if the horizontal deformation of the subway station is greater than or equal to the first preset threshold, the relevant parameters of the simulated excavation are not input into the prediction model, and the following steps are performed:

[0039] Re-conduct simulated excavation by combining two of the three planned excavation plots;

[0040] Comparing the horizontal deformation of the subway station with the first preset threshold, if the horizontal deformation of the subway station is less than the first preset threshold, inputting the data of the simulated excavation into the prediction model;

[0041] If the horizontal deformation of the subway station is greater than or equal to the first preset threshold, no data is input into the prediction model, and separate simulated excavation of the two planned excavation plots is re-performed, and the data is output to the prediction model.

[0042] On the other hand, the present invention provides a system for simulating horizontal deformation of a subway structure with a subway double-sided extension, which uses the method for simulating horizontal deformation of a subway structure with a subway double-sided extension in any of the above schemes to simulate horizontal deformation of a subway station, comprising:

[0043] The block division module is used to divide the soil to be excavated around the subway station into several plots to be excavated in the horizontal and vertical directions;

[0044] The numerical simulation module is used to perform numerical simulation excavation on the planned excavation plot, calculate the horizontal deformation of the subway station after a single simulated excavation, and output the corresponding horizontal deformation data;

[0045] A rate analysis module, used to determine the excavation rate according to the horizontal deformation corresponding to the excavation position of a single simulated excavation;

[0046] A training module, used to receive the output data of the numerical simulation module, and train the relationship between the excavation process and the horizontal deformation of the subway station through a neural network model to generate a prediction model;

[0047] A set generation module, used to determine, through a prediction model, a set of excavation procedures for which the horizontal deformation of the subway station is less than a preset value;

[0048] The process exclusion module is used to exclude the wrong excavation process in the excavation process set based on empirical data and construction standards;

[0049] The process output module is used to analyze the construction time based on the excavation rate from the excluded excavation process set, and output the optimal excavation process with the shortest construction period.

[0050] As a preferred technical solution for the horizontal deformation simulation system of subway structures for subway double-sided expansion, the sizes of the plots to be excavated divided by the block module are the same.

[0051] The beneficial effects of the present invention are:

[0052] The present invention provides a method for simulating the horizontal deformation of a subway structure with a subway being extended on both sides. The method for simulating the horizontal deformation of a subway structure with a subway being extended on both sides is established through numerical simulation of layered and block excavation and a neural network model of simulation data, and takes into account the influence of excavation rate on the horizontal deformation of the subway station. The method can effectively reduce the deformation influence of foundation pit excavation around the subway on the subway station while ensuring the construction period.

[0053] Furthermore, the present invention divides the soil to be excavated around the subway station into several plots to be excavated in the horizontal and vertical directions. This method can accurately control the amount of soil to be excavated each time, thereby reducing the risk of horizontal deformation during the excavation process. Compared with the traditional single excavation scheme, this layered and block-based approach allows for flexible adjustment of excavation strategies under complex geological conditions, reducing the possibility of ground instability and surrounding building settlement caused by sudden displacement of large-scale soil.

[0054] Furthermore, the present invention simulates the excavation of the proposed excavation plot and calculates the horizontal deformation of the subway station through numerical simulation. It can simulate different excavation schemes multiple times before construction and predict the possible deformation in advance. This process not only improves the accuracy of the prediction, but also enables the construction party to formulate a more targeted construction plan before excavation, avoiding the errors caused by insufficient data or simplified models in traditional methods, thereby reducing construction risks.

[0055] Furthermore, the present invention determines the excavation rate of the corresponding plot to be excavated according to the horizontal deformation corresponding to a single simulated excavation. This innovative design enables the construction process to be dynamically adjusted. In traditional construction, the excavation rate is often fixed in advance, which makes it difficult to cope with the geological conditions that change in real time during the construction process. However, this method effectively reduces the problem of stratum deformation caused by improper construction rate by calculating and adjusting the excavation rate in real time, thereby improving the safety and accuracy of construction.

[0056] Furthermore, the present invention determines the excavation process set with a horizontal deformation of the subway station less than a preset value through a prediction model, and can quickly select the optimal solution from a large number of excavation solutions, while reducing the computing power of the equipment and minimizing the risk of deformation. This method avoids the deviation that may occur under a single process or experience-based approach in traditional construction, and uses objective data predicted by the model to guide construction decisions, thereby improving the scientificity and reliability of the solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flow chart of a method for simulating horizontal deformation of a subway structure for subway double-sided extension in an embodiment of the present invention;

[0058] Figure 2 A cross-sectional schematic diagram of the division of a plot to be excavated in an embodiment of the present invention;

[0059] Figure 3 A schematic top view of the division of the land to be excavated in an embodiment of the present invention;

[0060] Figure 4 It is a structural block diagram of the horizontal deformation simulation system of the subway structure for subway double-sided extension in an embodiment of the present invention.

[0061] In the picture: 1. Subway station; 2. Land to be excavated. DETAILED DESCRIPTION

[0062] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] In the description of the present invention, it should be noted that the orientations or positional relationships indicated by the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. Among them, the terms "first position" and "second position" are two different positions, and the first feature "above", "above" and "above" the second feature include the first feature being directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. The first feature "below", "below" and "below" the second feature include the first feature being directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0064] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0065] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0066] like Figure 1 As shown, this embodiment provides a method for simulating horizontal deformation of a subway structure with a subway double-sided extension, and the method for simulating horizontal deformation of a subway structure with a subway double-sided extension includes:

[0067] Step S1, dividing the soil to be excavated around the subway station into a number of plots to be excavated in the horizontal and vertical directions;

[0068] Step S2, simulate excavation of the planned excavation plot through numerical simulation, and calculate the horizontal deformation of the subway station after a single simulated excavation;

[0069] Step S3, determining the excavation rate of the corresponding plot to be excavated according to the horizontal deformation corresponding to the single simulated excavation;

[0070] Step S4, training the relationship between the excavation process and the horizontal deformation of the subway station through a neural network model to obtain a prediction model to generate the horizontal deformation of the subway station corresponding to the excavation process;

[0071] Step S5, determining an excavation process set in which the horizontal deformation of the subway station is less than a preset value through a prediction model;

[0072] Step S6, eliminating wrong excavation processes in the excavation process set by using empirical data and construction standards;

[0073] Step S7, in the set of excavation processes that have been eliminated, determine the optimal excavation process with the shortest construction period according to the excavation rate of each simulated excavation.

[0074] In the above embodiment, by numerical simulation of layered and block excavation and establishment of a neural network model of simulation data, and taking into account the influence of excavation rate on the horizontal deformation of the subway station, it is possible to effectively reduce the deformation influence of the foundation pit excavation around the subway station on the subway station while ensuring the construction period.

[0075] Furthermore, by dividing the soil to be excavated around the subway station into several plots to be excavated in the horizontal and vertical directions, this method can accurately control the amount of soil to be excavated each time, thereby reducing the risk of horizontal deformation during the excavation process. Compared with the traditional single excavation scheme, this layered and block-by-layer approach allows flexible adjustment of the excavation strategy under complex geological conditions, reducing the possibility of stratum instability and surrounding building settlement caused by sudden displacement of large-scale soil. In detail, by simulating the excavation of the plot to be excavated through numerical simulation and calculating the horizontal deformation of the subway station, different excavation schemes can be simulated multiple times before construction to predict the possible deformation in advance. This process not only improves the accuracy of the prediction, but also enables the construction party to formulate a more targeted construction plan before excavation, avoiding the errors caused by insufficient data or simplified models in traditional methods, thereby reducing construction risks. And the excavation rate of the corresponding plot to be excavated is determined according to the horizontal deformation corresponding to a single simulated excavation. This innovative design enables the construction process to have the ability to dynamically adjust. In traditional construction, the excavation rate is often fixed in advance, which is difficult to cope with the real-time changing geological conditions during the construction process. This method effectively reduces the problem of ground deformation caused by improper construction rate by real-time calculation and adjustment of excavation rate, thereby improving the safety and accuracy of construction. In addition, the present invention determines the set of excavation procedures for subway stations with horizontal deformation less than the preset value through the prediction model, and can quickly select the optimal solution from many excavation solutions, while reducing the computing power of the equipment and minimizing the risk of deformation. It avoids the deviations that may occur under the guidance of a single process or experience in traditional construction, and uses the objective data predicted by the model to guide construction decisions, thereby improving the scientificity and reliability of the solution.

[0076] For easier understanding, see Figure 2 and Figure 3 As shown, illustratively, this embodiment provides a schematic diagram of a layered and block excavation, in which the soil to be excavated around the subway station 1 is divided into several blocks 2 to be excavated, so as to facilitate further analysis of the excavation process. Optionally, the blocks to be excavated are marked after the block division to reduce the computing power of the prediction model, and the blocks to be excavated are marked as Bijk, where i, j and k are the coordinates of the blocks to be excavated in three orthogonal directions, respectively.

[0077] Specifically, step S3 includes: comparing the horizontal deformation with a first deformation threshold, and if the horizontal deformation is less than the first deformation threshold, determining that the corresponding simulated excavation is performed at a standard excavation rate.

[0078] If the horizontal deformation is greater than or equal to the first deformation threshold, perform the following steps:

[0079] Step S31, dividing the land to be excavated into several layers;

[0080] Step S32, performing simulated excavation at a standard excavation rate for each layer in turn;

[0081] Step S33, determining a fault layer in which the horizontal deformation of the subway station in the simulated excavation of each layer is greater than a second deformation threshold;

[0082] Step S34, excavating the fault layer at an excavation rate that decreases step by step from the standard excavation rate until the horizontal deformation of the layer is less than the second deformation threshold or reaches the minimum excavation rate, and determining the excavation rate that meets the corresponding conditions as the layer excavation rate;

[0083] Calculate the excavation rate of the proposed excavation plot according to the determined excavation rates of each layer;

[0084] The second deformation threshold is determined according to the first deformation threshold and the number of layers of the planned excavation plot.

[0085] The preset value, the first deformation threshold and the standard excavation rate need to be determined in combination with the construction standards in the actual scene. The second deformation threshold can be the ratio of the first deformation threshold to the number of layers of the planned excavation plot.

[0086] Specifically, step S2 includes:

[0087] Step S21, before simulating excavation, inputting geological parameters related to the planned excavation plot and the subway station;

[0088] Step S22, calculating the horizontal deformation of the subway station during the excavation process through finite element analysis. The calculation of deformation parameters through numerical simulation methods such as finite element analysis during construction is a prior art and will not be repeated here.

[0089] Specifically, step S4 includes:

[0090] Step S41, obtaining a simulation data set;

[0091] Step S42, preprocessing the simulated data set to remove noise data and outliers;

[0092] Step S43, normalizing the simulated data set;

[0093] Step S44, dividing the normalized simulated data set into a training set and a validation set, wherein the training set is used for training the neural network model, and the validation set is used for evaluating the model performance;

[0094] Step S45, constructing a neural network model, the model includes an input layer, multiple hidden layers and an output layer, the input layer receives relevant parameters of the excavation process, and the output layer generates the horizontal deformation of the subway station;

[0095] The simulation data set includes the location of a single simulated excavation, the horizontal deformation of the subway station corresponding to the single simulated excavation, the simulated excavation process, and the horizontal deformation of the subway station after the simulated excavation process is executed. In detail, the simulated excavation process corresponding to the simulation data set is the excavation process after traversing all excavation processes and screening in step S3. The above neural network model can also be replaced by other neural network models that can combine simulation data to calculate the horizontal deformation of the subway station.

[0096] In step S6, the erroneous excavation process in the excavation process set is eliminated by using the empirical data and the construction standard. Since the prediction model lacks the combination with the actual experience, some excavation processes that are not in line with common sense or cannot be realized are output. At this time, the empirical data and the construction standard can effectively eliminate this phenomenon and improve the accuracy. Based on step S6, step S7 includes:

[0097] Step S71, counting the excavation rate corresponding to each simulated excavation in the excavation process;

[0098] Step S72, integrating and calculating the excavation rate of each simulated excavation to obtain the construction time of each excavation process;

[0099] Step S73, compare the construction time and determine the excavation process with the shortest construction time as the optimal excavation process. Determining the optimal excavation process can take into account both the construction period and the quality, and provide sufficient high-quality and reliable data support.

[0100] Specifically, the initial number of plots to be excavated corresponding to a single simulated excavation is three. The excavation of the plots to be excavated is simulated through numerical simulation, and the horizontal deformation of the subway station after a single simulated excavation is calculated, which also includes:

[0101] The excavation is simulated with the initial quantity, and the horizontal deformation of the subway station is compared with the first deformation threshold. If the horizontal deformation of the subway station is less than the first preset threshold, the data of the simulated excavation is input into the prediction model.

[0102] If the horizontal deformation of the subway station is greater than or equal to the first preset threshold, the relevant parameters of the simulated excavation are not input into the prediction model, and the following steps are performed:

[0103] Step S201, re-simulating excavation by combining two of the three plots to be excavated;

[0104] Step S202, comparing the horizontal deformation of the subway station with a first preset threshold value, if the horizontal deformation of the subway station is less than the first preset threshold value, inputting the data of the simulated excavation into the prediction model;

[0105] Step S203: If the horizontal deformation of the subway station is greater than or equal to the first preset threshold, the data is not input into the prediction model, and the two plots to be excavated are re-simulated for excavation, and the data is output to the prediction model. It can be understood that for the excavation of foundation pits, it is common to excavate multiple plots at the same time. During construction, the initial number can be determined according to the excavation area and the number of plots to be excavated. Through the above comparison, invalid data that cannot be realized can be screened out, reducing the computing power of the equipment.

[0106] See also Figure 4 As shown, this embodiment further provides a subway structure horizontal deformation simulation system for subway double-sided extension, which uses the subway structure horizontal deformation simulation method for subway double-sided extension in any of the above schemes to simulate the horizontal deformation of the subway station, including:

[0107] The block division module is used to divide the soil to be excavated around the subway station into several plots to be excavated in the horizontal and vertical directions;

[0108] The numerical simulation module is used to perform numerical simulation excavation on the planned excavation plot, calculate the horizontal deformation of the subway station after a single simulated excavation, and output the corresponding horizontal deformation data;

[0109] A rate analysis module, used to determine the excavation rate according to the horizontal deformation corresponding to the excavation position of a single simulated excavation;

[0110] A training module, for receiving the output data of the numerical simulation module, and training the relationship between the excavation process and the horizontal deformation of the subway station through a neural network model to generate a prediction model;

[0111] A set generation module, used to determine the excavation process set of the subway station whose horizontal deformation is less than a preset value through a prediction model;

[0112] The process exclusion module is used to exclude the wrong excavation process in the excavation process set based on empirical data and construction standards;

[0113] The process output module is used to analyze the construction time based on the excavation rate from the excluded excavation process set, and output the optimal excavation process with the shortest construction period.

[0114] Specifically, the sizes of the plots to be excavated divided by the block modules are the same, which can effectively improve the comparability of the excavation process and related parameters.

[0115] The modules involved in the embodiments described in this application may be implemented by software or hardware, and the modules described may also be set in a processor.

[0116] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the device, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based device that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0117] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for simulating horizontal deformation of subway structures for subway double-sided extension, characterized in that: include: Divide the soil to be excavated around the subway station into several plots to be excavated in the horizontal and vertical directions; Through numerical simulation, the proposed excavation site is simulated and the horizontal deformation of the subway station after a single simulated excavation is calculated; Determine the excavation rate of the corresponding plot to be excavated according to the horizontal deformation corresponding to a single simulated excavation; The relationship between the excavation process and the horizontal deformation of the subway station is trained through a neural network model to obtain a prediction model to generate the horizontal deformation of the subway station corresponding to the excavation process; Determine, by the prediction model, a set of excavation procedures in which the horizontal deformation of the subway station is less than a preset value; Eliminate incorrect excavation procedures in the excavation procedure set by using empirical data and construction standards; In the set of excavation processes that have been eliminated, the optimal excavation process with the shortest construction period is determined according to the excavation rate of each simulated excavation; The training of the relationship between the excavation process and the horizontal deformation of the subway station by a neural network model to generate the horizontal deformation of the subway station corresponding to the excavation process includes: Get a simulated data set; Preprocessing the simulated data set to remove noise data and outliers; Normalizing the simulated data set; The normalized simulated data set is divided into a training set and a validation set, where the training set is used to train the neural network model and the validation set is used to evaluate the model performance; Constructing a neural network model, the model comprising an input layer, a plurality of hidden layers and an output layer, the input layer receiving relevant parameters of the excavation process, and the output layer generating horizontal deformation of the subway station; The simulation data set includes the location of a single simulated excavation, the horizontal deformation of the subway station corresponding to the single simulated excavation, the simulated excavation process, and the horizontal deformation of the subway station after executing the simulated excavation process.

2. The method for simulating horizontal deformation of subway structures in subway double-sided extension according to claim 1 is characterized in that: The method of determining the excavation rate of the corresponding plot to be excavated based on the horizontal deformation corresponding to a single simulated excavation includes: comparing the horizontal deformation with a first deformation threshold, and if the horizontal deformation is less than the first deformation threshold, determining that the corresponding simulated excavation is performed at a standard excavation rate.

3. The method for simulating horizontal deformation of subway structure in subway double-sided extension according to claim 2 is characterized in that: The step of determining the excavation rate of the corresponding plot to be excavated according to the horizontal deformation amount corresponding to the single simulated excavation further includes, if the horizontal deformation amount is greater than or equal to the first deformation threshold, executing the following steps: Divide the land to be excavated into several layers; Simulate excavation for each layer in turn at the standard excavation rate; Determine the fault layer in which the horizontal deformation of the subway station in the simulated excavation of each layer is greater than a second deformation threshold; excavating the fault layer at an excavation rate that decreases step by step from the standard excavation rate until the horizontal deformation of the layer is less than the second deformation threshold or reaches the minimum excavation rate, and determining the excavation rate that meets the corresponding conditions as the layer excavation rate; Calculate the excavation rate of the proposed excavation plot according to the determined excavation rates of each layer; The second deformation threshold is determined according to the first deformation threshold and the number of layers of the planned excavation plot.

4. The method for simulating horizontal deformation of subway structure in subway double-sided extension according to claim 3 is characterized in that: The method of simulating excavation of the proposed excavation plot by numerical simulation and calculating the horizontal deformation of the subway station after a single simulated excavation comprises: Before simulating excavation, input geological parameters related to the proposed excavation site and the subway station; The horizontal deformation of the subway station during the excavation process is calculated through finite element analysis.

5. The method for simulating horizontal deformation of subway structure in subway double-sided extension according to claim 4 is characterized in that: The optimal excavation process with the shortest construction period determined according to the excavation rate of each simulated excavation includes: Statistically calculate the excavation rate corresponding to each simulated excavation in the excavation process; The excavation rate of each simulated excavation is integrated and calculated to obtain the construction time of each excavation process; The construction times are compared and the excavation process with the shortest construction time is determined as the optimal excavation process.

6. The method for simulating horizontal deformation of subway structure in subway double-sided extension according to claim 5 is characterized in that: The initial number of plots to be excavated corresponding to a single simulated excavation is three. The simulated excavation of the plots to be excavated by numerical simulation and the calculation of the horizontal deformation of the subway station after the single simulated excavation also include: The simulated excavation is performed with the initial quantity, and the horizontal deformation of the subway station is compared with the first deformation threshold. If the horizontal deformation of the subway station is less than the first preset threshold, the data of the simulated excavation is input into the prediction model.

7. The method for simulating horizontal deformation of subway structure in subway double-sided extension according to claim 6 is characterized in that: If the horizontal deformation of the subway station is greater than or equal to the first preset threshold, the relevant parameters of the simulated excavation are not input into the prediction model, and the following steps are performed: Re-conduct simulated excavation by combining two of the three planned excavation plots; Comparing the horizontal deformation of the subway station with the first preset threshold, if the horizontal deformation of the subway station is less than the first preset threshold, inputting the data of the simulated excavation into the prediction model; If the horizontal deformation of the subway station is greater than or equal to the first preset threshold, no data is input into the prediction model, and separate simulated excavation of the two planned excavation plots is re-performed, and the data is output to the prediction model.

8. A subway structure horizontal deformation simulation system for subway double-sided expansion, characterized in that: The method for simulating horizontal deformation of a subway structure with a subway double-sided extension as described in any one of claims 1 to 7 is applied, and the system for simulating horizontal deformation of a subway structure with a subway double-sided extension comprises: The block division module is used to divide the soil to be excavated around the subway station into several plots to be excavated in the horizontal and vertical directions; The numerical simulation module is used to perform numerical simulation excavation on the planned excavation plot, calculate the horizontal deformation of the subway station after a single simulated excavation, and output the corresponding horizontal deformation data; A rate analysis module, used to determine the excavation rate according to the horizontal deformation corresponding to the excavation position of a single simulated excavation; A training module, used to receive the output data of the numerical simulation module, and train the relationship between the excavation process and the horizontal deformation of the subway station through a neural network model to generate a prediction model; A set generation module, used to determine, through a prediction model, a set of excavation procedures for which the horizontal deformation of the subway station is less than a preset value; The process exclusion module is used to exclude the wrong excavation process in the excavation process set based on empirical data and construction standards; The process output module is used to analyze the construction time based on the excavation rate from the excluded excavation process set, and output the optimal excavation process with the shortest construction period.

9. The subway structure horizontal deformation simulation system for subway double-side extension according to claim 8 is characterized in that: The sizes of the plots to be excavated divided by the block module are the same.

Images