Deformation prediction method and device for supporting structure of foundation pit around densely packed buildings

Abstract

The present invention provides a method and device for predicting deformation of supporting structures of foundation pits around dense buildings, which can be applied to engineering construction and the field of artificial intelligence technology. The prediction method includes: obtaining excavation information of the foundation pit and soil information, supporting structure information and hydrological information corresponding to the foundation pit; inputting excavation information, soil information, vertical support information, horizontal support information, inertial information and hydrological information into a deformation prediction model, and outputting initial prediction results, wherein the initial prediction results include multiple horizontal deformation information, deformation peak values ​​and deformation types, and the horizontal deformation information characterizes the horizontal deformation results of multiple points in the supporting structure; based on multiple horizontal deformation information, deformation peak values ​​and deformation types, determining the target prediction results corresponding to the foundation pit. Through this method, the deformation of the supporting structure under complex load conditions can be predicted more accurately, so that the accuracy of the target prediction results is higher, and the safety, stability and economy of the foundation pit project are improved.

Description

Technical Field

[0001] The present invention relates to the fields of engineering construction and artificial intelligence technology, and in particular to a method and a device for predicting deformation of a supporting structure of a foundation pit around dense buildings. Background Art

[0002] During the excavation of foundation pits, the horizontal displacement of the supporting structure is one of the important factors affecting the stability and safety of the foundation pit. The excavation of foundation pits is faced with the situation of densely distributed buildings around them. In order to ensure the smooth progress of foundation pit construction and prevent adverse effects on the surrounding environment, by controlling the horizontal deformation of the supporting structure during construction, it is possible to prevent the supporting structure from deforming too much and causing damage to the foundation pit or surrounding buildings. In related technologies, the horizontal displacement monitoring and prediction methods for the supporting structure of foundation pit excavation mainly include monitoring the supporting structure using monitoring equipment (such as laser scanners, total stations, and levels); and using numerical models (such as finite element method, discrete element method, and empirical formula method) to predict the future displacement of the supporting structure.

[0003] The prediction method for support structure deformation in related technologies ignores the impact of dense buildings around the foundation pit on the deformation of the support structure, increases the safety hazards during the foundation pit excavation process, and the prediction results are low in accuracy; traditional monitoring methods usually rely on manual observation and regular monitoring, and the data collection and processing process is cumbersome, which makes it difficult to meet the real-time monitoring and early warning needs. Summary of the invention

[0004] In view of the above problems, the present invention provides a method, device, equipment, medium and program product for predicting deformation of supporting structures of foundation pits around densely populated buildings.

[0005] According to a first aspect of the present invention, a method for predicting deformation of a support structure of a foundation pit around densely populated buildings is provided, comprising: obtaining excavation information of the foundation pit and soil information, support structure information and hydrological information corresponding to the foundation pit, wherein the support structure information is determined based on dense building information around the foundation pit, including vertical support information, horizontal support information and inertial information; inputting the excavation information, soil information, vertical support information, horizontal support information, inertial information and hydrological information into a deformation prediction model, and outputting an initial prediction result, wherein the initial prediction result includes multiple horizontal deformation information, deformation peak values ​​and deformation types, and the horizontal deformation information characterizes the horizontal deformation results of multiple points in the support structure; and determining a target prediction result corresponding to the foundation pit based on the multiple horizontal deformation information, deformation peak values ​​and deformation types, and the deformation types include cantilever type, skirting type and convex type.

[0006] The second aspect of the present invention provides a support structure deformation prediction device for a foundation pit around dense buildings, including: an information acquisition module, used to acquire excavation information of the foundation pit and soil information, support structure information and hydrological information corresponding to the foundation pit, wherein the support structure information is determined based on the dense building information around the foundation pit, including vertical support information, horizontal support information and inertial information; an initial prediction result output module, used to input excavation information, soil information, vertical support information, horizontal support information, inertial information and hydrological information into a deformation prediction model, and output an initial prediction result, wherein the initial prediction result includes multiple horizontal deformation information, deformation peak values ​​and deformation types, and the horizontal deformation information characterizes the horizontal deformation results of multiple points in the support structure; and a target prediction result determination module, used to determine the target prediction result corresponding to the foundation pit based on multiple horizontal deformation information, deformation peak values ​​and deformation types, and the deformation types include cantilever type, skirting type and convex type.

[0007] A third aspect of the present invention provides an electronic device, comprising: one or more processors; a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0008] The fourth aspect of the present invention further provides a computer-readable storage medium on which a computer program or instruction is stored, and the steps of the above method are implemented when the above computer program or instruction is executed by a processor.

[0009] The fifth aspect of the present invention also provides a computer program product, including a computer program or instructions, which implement the steps of the above method when executed by a processor.

[0010] According to the method, device, equipment, medium and program product for predicting deformation of support structures of foundation pits around dense buildings provided by the present invention, by inputting excavation information, soil information, support structure information and hydrological information into the deformation prediction model, horizontal deformation information and deformation peak values ​​of multiple deformation types can be output in real time according to actual engineering needs, thereby avoiding the complexity and lag of traditional manual monitoring, improving the timeliness of target prediction results and the universality of prediction methods, and because the support structure information integrates the existing dense building information in the surrounding area, the vertical support information, horizontal support information and inertial information at different depth points can be used to more accurately predict the deformation of the support structure under complex load conditions, so that the accuracy of the target prediction results is higher, further improving the safety, stability and economy of the foundation pit project. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above contents and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings.

[0012] Figure 1 A diagram showing an application scenario of a method, device, equipment, medium and program product for predicting deformation of a supporting structure of a foundation pit around densely packed buildings according to an embodiment of the present invention.

[0013] Figure 2 A flow chart of a method for predicting deformation of supporting structures of foundation pits around densely packed buildings according to an embodiment of the present invention is shown.

[0014] Figure 3 A schematic diagram of deformation types of a support structure according to an embodiment of the present invention is shown.

[0015] Figure 4 Example graphs showing the accuracy of a deformation prediction model verified using multiple cases according to an embodiment of the present invention are shown, wherein (a) shows the displacement curve of case A, (b) shows the displacement curve of case B, and (c) shows the displacement curve of case C.

[0016] Figure 5 An example diagram showing a deformation prediction process of a supporting structure of a foundation pit around densely packed buildings according to an embodiment of the present invention is shown.

[0017] Figure 6 A structural block diagram of a device for predicting deformation of supporting structures of foundation pits around densely packed buildings according to an embodiment of the present invention is shown.

[0018] Figure 7 A block diagram of an electronic device suitable for implementing a method for predicting deformation of a supporting structure of a foundation pit around densely packed buildings according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0019] Below, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of concepts of the present invention.

[0020] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0021] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0022] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0023] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0024] In the technical solution of the present invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0025] In the process of conceiving the present invention, the inventors found that the prediction of the deformation of the foundation pit support structure in the related technology ignored the impact of the dense buildings around the foundation pit on the deformation of the support structure, increased the safety hazards during the foundation pit excavation process, and the prediction results were low in accuracy; traditional monitoring methods usually rely on manual observation and regular monitoring, and the data collection and processing process is cumbersome, which makes it difficult to meet the real-time monitoring and early warning needs.

[0026] In view of this, the present invention inputs excavation information, soil information, support structure information and hydrological information into the deformation prediction model, and can output horizontal deformation information and deformation peak values ​​of multiple deformation types in real time according to actual engineering needs, avoiding the complexity and lag of traditional manual monitoring, and improving the timeliness of target prediction results and the universality of prediction methods. Since the support structure information integrates the existing dense building information in the surrounding area, the vertical support information, horizontal support information and inertial information at different depth points can be used to more accurately predict the deformation of the support structure under complex load conditions, so that the target prediction results are more accurate, further improving the safety, stability and economy of foundation pit projects.

[0027] The embodiment of the present invention provides a method, device, equipment, medium and program product for predicting deformation of a support structure of a foundation pit around dense buildings. The method includes: obtaining excavation information of the foundation pit and soil information, support structure information and hydrological information corresponding to the foundation pit, wherein the support structure information is determined based on the dense building information around the foundation pit, including vertical support information, horizontal support information and inertial information; inputting the excavation information, soil information, vertical support information, horizontal support information, inertial information and hydrological information into a deformation prediction model, and outputting an initial prediction result, wherein the initial prediction result includes multiple horizontal deformation information, deformation peak values ​​and deformation types, and the horizontal deformation information represents the horizontal deformation results of multiple points in the support structure; and determining a target prediction result corresponding to the foundation pit based on the multiple horizontal deformation information, deformation peak values ​​and deformation types, and the deformation types include cantilever type, kicking type and convex type. .

[0028] Figure 1 A diagram showing an application scenario of a method, device, equipment, medium and program product for predicting deformation of a supporting structure of a foundation pit around densely packed buildings according to an embodiment of the present invention.

[0029] like Figure 1 As shown, the application scenario according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, a server 105, and an information collection device 106. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0030] There can be multiple information acquisition devices 106, which can be set at points with different depths on the supporting structure of the foundation pit. The specific number of information acquisition devices 106 and the spacing between adjacent information acquisition devices can be determined according to actual needs, and are not limited here. For example, the vertical spacing of the displacement meter can be set to 0.5-2m, and the restart can be set to arrange a displacement meter every 1 meter. The layout density can be readjusted according to the height of the structure in the later stage. The type of information acquisition equipment 106 can be determined according to actual engineering needs, and is not limited here, such as displacement meters, displacement sensors, total stations, inclinometers and strain gauges. The information acquisition equipment 106 can be connected to the server 105 through the network 104 to meet the transmission of information or data. The server 105 can analyze and process the collected information according to engineering needs.

[0031] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0032] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0033] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0034] It should be noted that the method for predicting deformation of supporting structures of foundation pits around dense buildings provided in the embodiment of the present invention can generally be executed by the server 105. Accordingly, the device for predicting deformation of supporting structures of foundation pits around dense buildings provided in the embodiment of the present invention can generally be set in the server 105. The method for predicting deformation of supporting structures of foundation pits around dense buildings provided in the embodiment of the present invention can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the device for predicting deformation of supporting structures of foundation pits around dense buildings provided in the embodiment of the present invention can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0035] It should be understood that Figure 1 The number of terminal devices, networks, information collection devices and servers in the embodiment is only for illustration. Any number of terminal devices, information collection devices, networks and servers may be provided according to the implementation requirements.

[0036] The following will be based on Figure 1 The scene described by Figure 2~Figure 5 A method for predicting deformation of supporting structures of foundation pits around densely packed buildings in a disclosed embodiment is described in detail.

[0037] Figure 2 A flow chart of a method for predicting deformation of supporting structures of foundation pits around densely packed buildings according to an embodiment of the present invention is shown.

[0038] like Figure 2 As shown, the method for predicting deformation of supporting structures of foundation pits around densely populated buildings in this embodiment includes operations S210 to S230.

[0039] In operation S210, excavation information of the foundation pit and soil information, support structure information and hydrological information corresponding to the foundation pit are obtained, wherein the support structure information is determined based on dense building information around the foundation pit, including vertical support information, horizontal support information and inertia information of multiple points with different depths.

[0040] In an embodiment of the present invention, excavation information, soil information, support structure information and hydrological information of the foundation pit can be obtained through different types of information collection equipment. The excavation information of the foundation pit can characterize the excavation size information, including excavation width and excavation depth. The soil information can characterize the soil information in the area surrounding the foundation pit support structure, and may include soil strength information, soil stress information and deformation capacity information, soft soil weight information and soft soil thickness information. The vertical support information may include vertical stiffness information and vertical displacement information, and the horizontal support information may characterize the horizontal support structure spacing. The inertial information may characterize the ability information of the support structure to resist bending deformation under the action of force.

[0041] In the embodiment of the present invention, the influence of existing dense buildings around the foundation pit on the support structure information is taken into account. For example, the load of dense buildings can act on the support structure through the soil, resulting in changes in the distribution of soil pressure, which can affect the design parameters of the support structure (stiffness, anti-overturning capacity and bearing capacity); at the same time, the foundation form of dense buildings (such as raft foundation, pile foundation, etc.) and the distribution density of existing building groups can produce complex coupling effects on the deformation mode and stress field of the soil around the foundation pit. This coupling effect can cause parameter mismatch in the design of the support structure. For example, the rationality of parameter information such as the spacing of supporting piles and pile diameters needs to be adjusted and optimized according to the characteristics of dense buildings. The complex interaction between the support structure and the existing dense buildings makes it difficult for traditional empirical methods to accurately describe the horizontal displacement changes of the foundation pit support. Ignoring these effects may cause the deformation of the support structure to exceed the standard range, affecting the safety of the foundation pit and the existing dense buildings around it. Therefore, the support structure information in the present invention can be determined based on the dense building information around the foundation pit.

[0042] In operation S220, excavation information, soil information, vertical support information, horizontal support information, inertial information and hydrological information are input into the deformation prediction model, and an initial prediction result is output, wherein the initial prediction result includes multiple horizontal deformation information, deformation peak values ​​and deformation types, and the horizontal deformation information characterizes the horizontal deformation results of multiple points in the support structure.

[0043] In an embodiment of the present invention, the deformation prediction model may be a model obtained by training the initial deformation prediction model using a hybrid algorithm of a multi-objective bird-flying optimization algorithm and a collaborative search optimization algorithm. The horizontal deformation information may characterize multiple horizontal deformation results corresponding to multiple points on the support structure, and the deformation peak value may characterize the maximum horizontal displacement value among multiple horizontal displacement results. The deformation type may be determined based on the depth position information of the point corresponding to the deformation peak value (maximum horizontal displacement value of the vertical support structure) on the support structure, and the deformation type may include a cantilever type, a kicking type, and an inward convex type.

[0044] In operation S230, a target prediction result corresponding to the foundation pit is determined based on the plurality of horizontal deformation information, deformation peak values, and deformation types, the deformation types including a cantilever type, a kicker type, and an inward convex type.

[0045] In an embodiment of the present invention, after determining the horizontal deformation information, deformation peak value and deformation type, the deformation curve of the support structure along the depth direction (target prediction result) can be further predicted. It can be understood that the cantilever type can characterize that the deformation curve of the support structure along the depth direction is a cantilever type displacement deformation; the kicking type can characterize that the deformation curve of the support structure along the depth direction is a kicking type displacement deformation; the convex type can characterize that the deformation curve of the support structure along the depth direction is a convex type displacement deformation.

[0046] In a feasible embodiment, after obtaining the excavation information, soil information, support structure information and hydrological information of the foundation pit, filtering technology can be used to remove noise data and improve data quality to ensure the accuracy of subsequent information processing results. The initial prediction results and target prediction results can use data visualization technology to convert the result information into intuitive graphics or tables, and update dynamic charts in real time. For example, the deformation results obtained by actual monitoring and the deformation curves obtained by model prediction are displayed on the same graph to guide subsequent engineering construction adjustments and deformation risk control strategies.

[0047] According to an embodiment of the present invention, by inputting excavation information, soil information, support structure information and hydrological information into a deformation prediction model, horizontal deformation information and deformation peak values ​​of multiple deformation types can be output in real time according to actual engineering needs, thereby avoiding the complexity and lag of traditional manual monitoring, and improving the timeliness of target prediction results and the universality of prediction methods. Since the support structure information integrates the surrounding existing dense building information, the vertical support information, horizontal support information and inertial information based on different depth points can be used to more accurately predict the deformation of the support structure under complex load conditions, so that the target prediction results are more accurate, further improving the safety, stability and economy of foundation pit engineering.

[0048] It can be understood that the above has explained how to determine the target prediction result, and the following will explain how to output the initial prediction result.

[0049] According to an embodiment of the present invention, the excavation information includes excavation width information and excavation depth information, and the soil information includes strength information, stress information, deformation modulus information and physical information;

[0050] The excavation information, soil information, vertical support information, horizontal support information, inertial information and hydrological information are input into the deformation prediction model, and the initial prediction results are output, including: the excavation width information, excavation depth information, strength information, stress information, deformation modulus information, physical information, vertical support information, horizontal support information, inertial information and hydrological information are input into the deformation prediction model to obtain multiple horizontal deformation information, deformation peak values ​​and deformation types.

[0051] In the embodiment of the present invention, the excavation width can be recorded as W, and the excavation depth can be recorded as H. e The soil strength information can be used to characterize the undrained shear strength, denoted as c u , soil stress information can represent the effective stress of the soil, denoted as σ v , the deformation capacity information can characterize the Young's modulus of the soil, denoted by E s , the physical information of the soil can include soft soil weight information and soft soil thickness information. The soft soil weight information can be recorded as γ s , the soft soil thickness information can be recorded as S. The vertical stiffness information can represent the stiffness of the vertical support structure, recorded as EI; the vertical displacement information can represent the maximum horizontal displacement of the vertical support structure, recorded as δ hm , moment of inertia (I), the horizontal horizontal support structure spacing can be recorded as h avg , inertial information can represent the moment of inertia, denoted as I. Hydrological information can represent the weight of water in the soil around the support structure, denoted as γ w The deformation prediction model can be constructed by updating and optimizing multiple initial parameters of the initial deformation prediction model and obtaining target parameters.

[0052] It can be understood that an example of how to output the initial prediction result has been described above, and an example of how to determine the deformation type of the support structure will be described below.

[0053] According to an embodiment of the present invention, the method further includes: determining the deformation type based on depth information of the target point corresponding to the deformation peak among the multiple points.

[0054] Figure 3 A schematic diagram of deformation types of a support structure according to an embodiment of the present invention is shown.

[0055] like Figure 3As shown, in an embodiment of the present invention, when there are existing dense buildings 320 around the foundation pit 310, the existing dense buildings 320 can cause deformation and displacement of the support structure 330, and then in the depth direction of the support structure 330 along the foundation pit. The acquisition device 340 can be used to collect the deformation results of multiple points, and the point where the deformation displacement reaches the peak value among the multiple points is determined as the target point. The deformation type of the support structure 330 can be divided into a cantilever type 301, an inward convex type 302 and a kicking type 303 according to the depth information of the target point (peak point). The deformation type of the support structure 330 can be determined as a cantilever type 301 in which one end (for example, the bottom end) of the support structure 330 is fixed and the other end (for example, the top end) is free to droop or displace; the deformation type of the support structure 330 that pushes outward or kicks out at one end (for example, the bottom end or a lower depth) can be determined as a kicking type 303; and the deformation type of the support structure 330 that is concave or bent inward toward the foundation pit side can also be determined as an inward convex type 302. It can be understood that in the cantilever type 301 deformation, the target point is located at the top of the support structure 330, in the kick-type 303 deformation, the target point is located at the bottom of the support structure 330, and in the convex type 302 deformation, the target point is located in the middle of the support structure 330.

[0056] According to an embodiment of the present invention, by determining the deformation type based on the deformation peak value of the foundation pit support structure and its corresponding depth information, it is possible to more accurately identify the deformation type, optimize the support design, improve construction safety and efficiency, reduce risks, and support long-term monitoring and maintenance. It provides an important monitoring means for foundation pit projects and ensures the stability and safety of the foundation pit support structure. After identifying the deformation type, the foundation pit support plan can be optimized in a targeted manner. For example, for cantilever type deformation, the upper stability of the support structure can be strengthened; for kick-type deformation, it is possible to consider reinforcing the bottom of the foundation pit or improving the ability to resist lateral pressure; for convex type deformation, it is possible to increase the lateral support of the support structure or adjust the support force of the soil around the foundation pit. This method can provide more accurate feedback to relevant technical personnel, so that timely adjustments can be made during the foundation pit construction process to ensure construction safety and structural stability.

[0057] It can be understood that an example of how to determine the deformation type of the support structure has been described above, and an example of how to determine the first deformation result in the target prediction result will be described below.

[0058] According to an embodiment of the present invention, the support structure information also includes a burial depth value, and the target prediction result includes a first deformation result corresponding to the cantilever type; the target prediction result corresponding to the foundation pit is determined based on multiple horizontal deformation information, deformation peak values ​​and deformation types, including: obtaining point depth values ​​corresponding to each of the multiple horizontal deformation information; and when the deformation type is a cantilever type, determining the first deformation result based on the point depth value, horizontal deformation information, deformation peak value and burial depth value.

[0059] In an embodiment of the present invention, the buried depth value may represent the total length of the support structure in the foundation pit depth direction, which may be recorded as H. The point depth value may include different point depths along the support structure downward vertically below the ground surface. The first deformation result may represent the horizontal deformation displacement value of the support structure during cantilever type deformation.

[0060] In an embodiment of the present invention, after determining the deformation type of the vertical support structure, the predicted value of the maximum horizontal displacement of the vertical support structure can be used. , determine the deformation result of the support structure along the depth direction. In the case of cantilever type deformation of the vertical support structure, the horizontal deformation curve of the support structure when the foundation pit is excavated at a future time can be determined, as shown in the following formula (1):

[0061] (1);

[0062] Among them, z can represent the different depths of the point vertically below the surface along the support structure (point depth value), It can characterize the horizontal deformation displacement of the vertical support structure at different depths during cantilever type deformation, and H can characterize the total length (buried depth value) of the foundation pit support structure along the depth direction.

[0063] It can be understood that an example of how to determine the first deformation result has been described above, and an example of how to determine the second deformation result in the target prediction result will be described below.

[0064] According to an embodiment of the present invention, the target prediction result also includes a second deformation result corresponding to the kicking type; the target prediction result corresponding to the foundation pit is determined based on multiple horizontal deformation information, deformation peak values ​​and deformation types, including: when the deformation type is the kicking type, the second deformation result is determined based on the burial depth value, point depth value and deformation peak value.

[0065] In an embodiment of the present invention, the second deformation result can represent the horizontal deformation displacement value of the support structure when the kicking type deformation occurs. When the vertical support structure is a kicking type deformation, the horizontal deformation curve of the support structure when the foundation pit is excavated in the future time period can be determined, as shown in the following formula (2):

[0066] (2);

[0067] in, The horizontal displacement deformation results of the vertical support structure at different depths when the kick-type deformation occurs can be characterized.

[0068] It can be understood that the above has described an example of how to determine the second deformation result in the target prediction result, and the following will describe how to determine the third deformation result in the target prediction result.

[0069] According to an embodiment of the present invention, the target prediction result also includes a third deformation result corresponding to the convex type, and the excavation information also includes a foundation pit depth value; the target prediction result corresponding to the foundation pit is determined based on multiple horizontal deformation information, deformation peak values ​​and deformation types, including: when the deformation type is the convex type, the point depth value is compared with the foundation pit depth value and the burial depth value to obtain a comparison result; and based on the comparison result, deformation peak value, burial depth value, foundation pit depth value and point depth value, the third deformation result is determined.

[0070] In an embodiment of the present invention, the foundation pit depth value can represent the design depth of the foundation pit excavation, which is recorded as L. By comparing the point depth value z with the foundation pit depth value L and the buried depth value H, the third deformation result can be determined, and the third deformation result can represent the horizontal deformation displacement value of the support structure when the deformation is an inward convex type. When the point depth value z is less than or equal to the foundation pit depth value L, the horizontal displacement deformation result of the first substructure segment in the support structure can be determined when the deformation is an inward convex type; when the point depth value z is greater than the foundation pit depth value L and less than or equal to the buried depth value, the horizontal displacement deformation result of the second substructure segment in the support structure can be determined when the deformation is an inward convex type. It can be understood that z≥0.

[0071] It can be understood that an example of how to determine the third deformation result in the target prediction result has been described above, and how to determine the third deformation result in the target prediction result will be further described below.

[0072] According to an embodiment of the present invention, a third deformation result is determined based on the comparison result, the burial depth value, the foundation pit depth value and the point depth value, including: when the comparison result indicates that the point depth value is less than or equal to the foundation pit depth value, the third deformation result is determined based on the deformation peak value, the foundation pit depth value and the point depth value; and when the comparison result indicates that the point depth value is greater than the foundation pit depth value and less than or equal to the burial depth value, the third deformation result is determined based on the deformation peak value, the foundation pit depth value, the point depth value and the burial depth value.

[0073] In the embodiment of the present invention, when the vertical support structure is an inward convex deformation, the horizontal deformation curve of the support structure when the foundation pit is excavated at a future time can be determined, as shown in the following formulas (3)-(4):

[0074] (3);

[0075] (4);

[0076] in, It can characterize the horizontal displacement deformation results of the first substructure section of the support structure (the distance from the ground surface to the designed excavation depth) during the convex deformation; It can characterize the horizontal displacement deformation results of the second substructure section of the support structure (the distance from the designed excavation depth to the bottom of the support structure) during the inward convex deformation; L can characterize the designed depth of the foundation pit excavation (foundation pit depth value).

[0077] It can be understood that the above has further explained an example of how to determine the third deformation result in the target prediction result, and the following will explain how to train the deformation prediction model.

[0078] According to an embodiment of the present invention, the deformation prediction model is trained by the following operations: obtaining sample excavation information of the sample foundation pit and sample soil information, sample support structure information and sample hydrological information corresponding to the sample foundation pit, wherein the sample support structure information is determined based on dense building information around the sample foundation pit, including sample vertical support information, sample horizontal support information and sample inertia information; and using the sample excavation information, sample soil information, sample vertical support information, sample horizontal support information, sample inertia information and sample hydrological information and their respective corresponding labels to train an initial deformation prediction model to obtain a deformation prediction model.

[0079] In an embodiment of the present invention, the sample excavation information, sample soil information, sample support structure information and sample hydrological information may be obtained by monitoring the sample foundation pit through information acquisition equipment, or may be sample information stored in a specific system or database. A hybrid algorithm of a Birds Optimization Algorithm (BOA) and an optimization algorithm based on swarm intelligence (e.g., collaborative search optimization) may be used to update and optimize multiple initial parameters of the initial deformation prediction model to obtain a deformation prediction model.

[0080] In an embodiment of the present invention, the initial prediction model uses sample excavation information, sample soil information, sample vertical support information, sample horizontal support information, sample inertia information, sample hydrological information and initial parameters to construct the initial prediction model, as shown in the following formula (5):

[0081] (5);

[0082] Among them, δ hmIt can represent the vertical displacement information and the maximum horizontal displacement of the vertical support structure, c u It can characterize the undrained shear strength, σ v It can characterize the effective stress of soil, E s It can characterize the soil Young's modulus, γ s It can represent the weight of soft soil, S can represent the thickness of soft soil, W can represent the width of foundation pit excavation, H e It can represent the excavation depth of the foundation pit, EI can represent the stiffness of the vertical support structure, I can represent the moment of inertia, h avg It can characterize the average horizontal support structure spacing. α1, α2, α3, α4, α5, α6, α7, and α8 are initial parameters respectively. w It can represent the gravity of water.

[0083] For example, the hybrid algorithm MFO-CSO of the Multi-Objective Moth-Flame Optimization (MFO) and the Collaborative Search Optimization (CSO) can be used to update and optimize multiple initial parameters of the initial deformation prediction model to obtain the deformation prediction model.

[0084] In the embodiment of the present invention, the flying bird optimization algorithm itself has a strong global search capability, and the collaborative search optimization can further accelerate convergence through information sharing and coordination to avoid falling into the local optimum too early in the initial stage. The hybrid algorithm can show a faster convergence speed and avoid the common problem of slow convergence in traditional optimization algorithms; compared with the traditional single-objective optimization algorithm, the hybrid algorithm can improve the search efficiency while optimizing multiple objectives, reduce redundant calculations, and thus reduce the computational cost.

[0085] It can be understood that the above has further explained an example of how to train a deformation prediction model, and the following will further explain how to train a deformation prediction model.

[0086] According to an embodiment of the present invention, the deformation prediction model includes multiple target parameters; the target parameters are updated by the following operations: determining an initial population and a target function corresponding to the initial parameters of the initial deformation prediction model, wherein the initial population includes multiple individuals, the individuals characterize the initial parameters, and the target function is obtained based on the monitoring values ​​and prediction values ​​corresponding to the sample foundation pit; updating the initial position information of the initial population based on the first update strategy and the target function to obtain intermediate position information; and cyclically updating the intermediate position information based on the second update strategy, the update step size and the position information of the target individual until a preset stop strategy is met to obtain the target parameters, wherein the preset stop strategy includes at least one of the following: the rate of change of the target function is less than a preset threshold and the number of iterations reaches a preset number threshold.

[0087] In an embodiment of the present invention, the target parameter is a model parameter after the initial parameter is updated and optimized using a hybrid algorithm. The objective function can characterize the horizontal displacement deformation result of the support structure obtained by actually monitoring the deformation monitoring device in the information acquisition device. The first update strategy can characterize the multi-objective flying bird optimization algorithm (MFO), the second update strategy can characterize the collaborative search optimization (CSO) strategy, and the update step size can characterize the search step size in the global and local search algorithms. The position information can characterize the specific value of each individual in the parameters (α1 to α8) in the global and local search algorithms.

[0088] In a feasible embodiment, the method of optimizing initial parameters using the hybrid algorithm MFO-CSO includes operations S410 to S470.

[0089] In operation S410, an initial population including initial parameters is generated. An initial population including 8 parameters α1, α2, α3, α4, α5, α6, α7, and α8 is randomly generated. Each individual in the initial population can represent a set of parameter values ​​to be optimized. The population size is defined as N and the maximum number of iterations is defined as T. The current position and current speed of the flock of birds are initialized. All individuals are randomly distributed in the parameter space, and the parameter space range is a real number. It can be understood that α1 to α8 can be a group of birds, and N can represent a population composed of N birds. The current position can represent the specific value of each individual in α1 to α8; the current speed can represent the amount of change in the parameters of the bird in each round of iteration, which can affect the direction (the amount of change can be a positive or negative number) and amplitude (the size of the amount of change) of the update of each individual of parameters α1 to α8.

[0090] In operation S420, define the objective function. The objective function can be defined based on the actual data of the horizontal displacement of the support structure actually monitored by the monitoring device. The objective function is the mean square error between the actual monitored displacement value and the predicted value of the model, as shown in the following formula (6):

[0091] (6);

[0092] in, The objective function can be represented as It can represent the maximum horizontal displacement value of the vertical support structure obtained by the actual monitoring for the i-th time. is the maximum horizontal displacement value of the vertical support structure measured by the deformation prediction model for the i-th time. α can represent the parameters to be optimized (initial parameters) α1, α2, α3, α4, α5, α6, α7, and α8.

[0093] In operation S430, a multi-objective bird optimization algorithm (MFO) is used to perform a global search. The flight path of the bird in the multi-dimensional space can be simulated to explore the global optimal solution, and the position of the bird is updated: the position vector of the bird is updated according to the distance between the current position of each bird and the optimal position. As shown in the following formula (7):

[0094] (7);

[0095] in, It can represent the position of the i-th bird in the current iteration. It can represent the optimal position of the current population. , It can be represented as a random number with a value range of [0,1] and uniform distribution. d The parameters in the spiral path can be characterized (L d It can be a distance control parameter between the flying bird and the optimal solution, which can affect the size and shape of the spiral trajectory of the flying bird flying around the optimal solution in the solution space).

[0096] In operation S440, the global optimal solution is updated. After each iteration, the objective function can be used to evaluate the fitness of the current bird population, and the parameters of the best bird are selected as the global optimal solution. The optimal position of the current population The calculation method of is shown in the following formula (8):

[0097] (8);

[0098] Xi(t) where t represents the number of iterations, Xi can represent the vector information of the current position of each bird in the i-th iteration. For example, after 100 iterations, Xi can represent the vector information of the current position of each bird in Xi(100) after completing 100 iterations, that is, Xi=[a1,a2,...,a8].

[0099] In operation S450, a local search is performed using collaborative search optimization (CSO). Local search can be performed near the current global optimal solution to further improve the accuracy of the solution. Through the collaborative search mechanism, individuals are guided to make fine adjustments around the global optimal solution, and the current global optimal solution can be optimized. And the relative position adjustment between individuals. As shown in the following formula (9):

[0100] (9);

[0101] in, , The positions of two randomly selected individuals can be characterized separately; It can represent the search step size and is used to control the scope of the local search. The value range is [0,1] and is evenly distributed.

[0102] Furthermore, the multi-objective flying bird optimization algorithm (MFO) and the collaborative search optimization (CSO) can be combined to perform global search and local search respectively, and perform multiple rounds of iterations. After each global search using MFO, CSO can be used for local search to ensure that the algorithm can jump out of the local optimal solution and improve the accuracy of the solution. The iteration can be stopped when one of the following preset stopping strategies is met. The preset stopping strategy can include that the value change of the objective function is less than the set threshold or the maximum number of iterations is reached.

[0103] In operation S460, the target parameters are output. After the iteration is stopped, the optimized target parameters can be recorded as α'1, α'2, α'3, α'4, α'5, α'6, α'7, and α'8, and substituted into the initial deformation prediction model to obtain the deformation prediction model, and perform displacement deformation prediction of the support structure, as shown in the following formula (10):

[0104] (10);

[0105] In operation S470, the prediction result is verified. Afterwards, the predicted value can be compared with the deformation result obtained by actual monitoring for verification. If the prediction error is less than the set 2% threshold, it is considered that the initial parameter optimization is reasonable and the prediction result is valid, and then the deformation prediction model is obtained. The verification method of the prediction result is shown in the following formula (11):

[0106] (11);

[0107] in, It can represent the error between the predicted value and the actual value. It can represent the maximum horizontal displacement value of the vertical support structure obtained by the actual monitoring for the i-th time. It can represent the maximum horizontal displacement value of the vertical support structure measured by the deformation prediction model for the i-th time.

[0108] According to an embodiment of the present invention, the combination of multi-objective bird's eye optimization and collaborative search optimization can enhance the robustness of the algorithm, especially in the face of uncertainty, noise and changing environments. For the optimization of deformation prediction model parameters, the algorithm can adapt to different types of input information (such as soil information, support structure information, hydrological information and excavation information) or deformation patterns to avoid overfitting or underfitting of the model during the training process.

[0109] Figure 4 An example diagram showing the accuracy of a deformation prediction model verified by using multiple cases according to an embodiment of the present invention.

[0110] like Figure 4 As shown in (a) in Figure 1, the accuracy of the deformation prediction model can be verified by using different foundation pit case information. In case A, the excavation depth of the foundation pit is H e It is 16.68m. The horizontal displacement data of the supporting structure is monitored based on the measuring points, and the displacement curve (convex type) predicted by the deformation prediction model is used for verification.

[0111] Substituting the optimized and updated model parameters into the deformation prediction model, the value of the horizontal displacement deformation of the support structure when the foundation pit is excavated in the future can be predicted. If it is greater than the threshold required by the specification, an alarm can be issued to relevant personnel through the alarm unit in the deformation monitoring management platform. The relevant parameters and prediction results are shown in Tables 1 to 3 below.

[0112] Table 1

[0113]

[0114] Table 2

[0115]

[0116] The maximum horizontal displacement of the supporting structure predicted based on the above parameters The comparison results with Case A are shown in Table 3 below, which shows that the deformation prediction model has higher accuracy.

[0117] Table 3

[0118]

[0119] like Figure 4 As shown in Figure (b), in Case B, the excavation depth of the foundation pit is H eThe horizontal displacement data of the support structure obtained from the actual monitoring of the measuring point is verified with the displacement curve (type of kicking foot) determined by the necessary prediction results obtained by the deformation prediction model. The optimized and updated parameters are substituted into the deformation prediction model to predict the value of the horizontal displacement of the support when the foundation pit is excavated in the future. If it is greater than the threshold required by the specification, an alarm can be issued to the relevant technical personnel through the alarm unit in the deformation monitoring management platform. The specific relevant parameters and prediction results are shown in Tables 4 to 6 below.

[0120] Table 4

[0121]

[0122] Table 5

[0123]

[0124] The maximum horizontal displacement of the supporting structure predicted based on the above parameters The comparison results with Case B are as follows, which shows that the prediction model has higher accuracy.

[0125] Table 6

[0126]

[0127] like Figure 4 As shown in Figure (c), in Case C, the excavation depth of the foundation pit is H e The horizontal displacement data of the monitoring support structure based on the measuring point is verified with the displacement curve (cantilever type) drawn by the horizontal displacement prediction model. The optimized and updated parameters are substituted into the deformation prediction model to predict the value of the horizontal displacement of the support when the foundation pit is excavated in the future. If it is greater than the threshold required by the specification, an alarm can be issued to the relevant technical personnel through the alarm unit in the deformation monitoring management platform. The specific relevant parameters and prediction results are shown in Tables 7 to 9 below.

[0128] Table 7

[0129]

[0130] Table 8

[0131]

[0132] The maximum horizontal displacement of the supporting structure predicted based on the above parameters The comparison results with Case C are shown in Table 9, which shows that the deformation prediction model has high accuracy.

[0133] Table 9

[0134]

[0135] Figure 5 An example diagram showing a deformation prediction process of a supporting structure of a foundation pit around densely packed buildings according to an embodiment of the present invention is shown.

[0136] like Figure 5 As shown, the basic information 510 of the foundation pit (including excavation information 511, soil information 512, support structure information 513 and hydrological information 514) can be obtained by using information acquisition equipment; thereby, the excavation information 511, soil information 512, support structure information 513 and hydrological information 514 are input into the deformation prediction model 520, and an initial prediction result 530 can be obtained. The initial prediction result 530 can include multiple horizontal deformation information 531, deformation peak value 532 and deformation type 533, and the horizontal deformation information characterizes the horizontal deformation results of multiple points in the support structure; and then based on the multiple horizontal deformation information 531, deformation peak value 532 and deformation type 533, the target prediction result 540 corresponding to the foundation pit is determined.

[0137] Based on the above method for predicting deformation of supporting structures of foundation pits around dense buildings, the present invention also provides a device for predicting deformation of supporting structures of foundation pits around dense buildings. Figure 6 The device is described in detail.

[0138] Figure 6 A structural block diagram of a device for predicting deformation of supporting structures of foundation pits around densely packed buildings according to an embodiment of the present invention is shown.

[0139] like Figure 6 As shown, the device for predicting deformation of supporting structures of foundation pits around densely populated buildings in this embodiment includes an information acquisition module 610, an initial prediction result output module 620 and a target prediction result determination module 630.

[0140] The information acquisition module 610 is used to obtain excavation information of the foundation pit and soil information, support structure information and hydrological information corresponding to the foundation pit, wherein the support structure information is determined based on the dense building information around the foundation pit, including vertical support information, horizontal support information and inertia information. In one embodiment, the information acquisition module 610 can be used to perform the operation S210 described above, which will not be repeated here.

[0141] The initial prediction result output module 620 is used to input excavation information, soil information, vertical support information, horizontal support information, inertial information and hydrological information into the deformation prediction model, and output the initial prediction result, wherein the initial prediction result includes multiple horizontal deformation information, deformation peak value and deformation type, and the horizontal deformation information represents the horizontal deformation results of multiple points in the support structure. In one embodiment, the initial prediction result output module 620 can be used to perform the operation S220 described above, which will not be repeated here.

[0142] The target prediction result determination module 630 is used to determine the target prediction result corresponding to the foundation pit based on multiple horizontal deformation information, deformation peak values ​​and deformation types, where the deformation types include cantilever type, kicker type and convex type. In one embodiment, the target prediction result determination module 630 can be used to perform the operation S230 described above, which will not be repeated here.

[0143] According to an embodiment of the present invention, through the information acquisition module 610, the initial prediction result output module 620 and the target prediction result determination module 630 in the support structure deformation prediction device for the foundation pit around dense buildings, by inputting the excavation information, soil information, support structure information and hydrological information into the deformation prediction model, the horizontal deformation information and deformation peak values ​​of multiple deformation types can be output in real time according to the actual engineering needs, thereby avoiding the complexity and lag of traditional manual monitoring, improving the timeliness of the target prediction results and the universality of the prediction method, and because the support structure information integrates the existing dense building information in the surrounding area, the vertical support information, horizontal support information and inertial information at different depth points can be used to more accurately predict the deformation of the support structure under complex load conditions, so that the accuracy of the target prediction results is higher, further improving the safety, stability and economy of the foundation pit project.

[0144] According to an embodiment of the present invention, the excavation information includes excavation width information and excavation depth information, and the soil information includes strength information, stress information, deformation modulus information and physical information; the initial prediction result output module 620 includes: an information input submodule, used to input the excavation width information, excavation depth information, strength information, stress information, deformation modulus information, physical information, vertical support information, horizontal support information, inertia information and hydrological information into the deformation prediction model to obtain multiple horizontal deformation information, deformation peak values ​​and deformation types.

[0145] According to an embodiment of the present invention, the device further comprises: a deformation type determination module, configured to determine the deformation type based on depth information of a target point corresponding to a deformation peak value among multiple points.

[0146] According to an embodiment of the present invention, the support structure information further includes a buried depth value, and the target prediction result includes a first deformation result corresponding to the cantilever type; the target prediction result determination module 630 includes: a depth value acquisition submodule and a first deformation result determination submodule. The depth value acquisition submodule is used to acquire a point depth value corresponding to each of the plurality of horizontal deformation information; and the first deformation result determination submodule is used to determine the first deformation result based on the point depth value, the horizontal deformation information, the deformation peak value and the buried depth value when the deformation type is the cantilever type.

[0147] According to an embodiment of the present invention, the target prediction result also includes a second deformation result corresponding to the kicking type; the target prediction result determination module 630 also includes: a second deformation result determination submodule, which is used to determine the second deformation result based on the burial depth value, point depth value and deformation peak value when the deformation type is the kicking type.

[0148] According to an embodiment of the present invention, the target prediction result also includes a third deformation result corresponding to the inward convex type, and the excavation information also includes a foundation pit depth value; the target prediction result determination module 630 also includes: a depth value comparison submodule and a third deformation result determination submodule. The depth value comparison submodule is used to compare the point depth value with the foundation pit depth value and the buried depth value to obtain a comparison result when the deformation type is the inward convex type; and the third deformation result determination submodule is used to determine the third deformation result based on the comparison result, the deformation peak value, the buried depth value, the foundation pit depth value and the point depth value.

[0149] According to an embodiment of the present invention, the third deformation result determination submodule includes: a third deformation result determination unit and a deformation result determination unit. The third deformation result determination unit is used to determine the third deformation result based on the deformation peak value, the foundation pit depth value and the point depth value when the comparison result indicates that the point depth value is less than or equal to the foundation pit depth value; and the deformation result determination unit is used to determine the third deformation result based on the deformation peak value, the foundation pit depth value, the point depth value and the burial depth value when the comparison result indicates that the point depth value is greater than the foundation pit depth value and less than or equal to the burial depth value.

[0150] According to an embodiment of the present invention, the deformation prediction model is trained by the following operations: obtaining sample excavation information of the sample foundation pit and sample soil information, sample support structure information and sample hydrological information corresponding to the sample foundation pit, wherein the sample support structure information is determined based on dense building information around the sample foundation pit, including sample vertical support information, sample horizontal support information and sample inertia information; and using the sample excavation information, sample soil information, sample vertical support information, sample horizontal support information, sample inertia information and sample hydrological information and their respective corresponding labels to train an initial deformation prediction model to obtain a deformation prediction model.

[0151] According to an embodiment of the present invention, the deformation prediction model includes multiple target parameters; the target parameters are updated by the following operations: determining an initial population and a target function corresponding to the initial parameters of the initial deformation prediction model, wherein the initial population includes multiple individuals, the individuals characterize the initial parameters, and the target function is obtained based on the monitoring values ​​and prediction values ​​corresponding to the sample foundation pit; updating the initial position information of the initial population based on the first update strategy and the target function to obtain intermediate position information; and cyclically updating the intermediate position information based on the second update strategy, the update step size and the position information of the target individual until a preset stop strategy is met to obtain the target parameters, wherein the preset stop strategy includes at least one of the following: the rate of change of the target function is less than a preset threshold and the number of iterations reaches a preset number threshold.

[0152] According to an embodiment of the present invention, any multiple modules of the information acquisition module 610, the initial prediction result output module 620 and the target prediction result determination module 630 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present invention, at least one of the information acquisition module 610, the initial prediction result output module 620 and the target prediction result determination module 630 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the information acquisition module 610, the initial prediction result output module 620 and the target prediction result determination module 630 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.

[0153] Figure 7 A block diagram of an electronic device suitable for implementing a method for predicting deformation of a supporting structure of a foundation pit around densely packed buildings according to an embodiment of the present invention is shown.

[0154] like Figure 7As shown, the electronic device according to an embodiment of the present invention includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 to a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0155] In RAM 703, various programs and data required for the operation of the electronic device are stored. The processor 701, ROM 702 and RAM 703 are connected to each other via a bus 704. The processor 701 performs various operations of the method flow according to the embodiment of the present invention by executing the programs in ROM 702 and / or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703. The processor 701 can also perform various operations of the method flow according to the embodiment of the present invention by executing the programs stored in the one or more memories.

[0156] According to an embodiment of the present invention, the electronic device may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device may further include one or more of the following components connected to the input / output (I / O) interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage portion 708 as needed.

[0157] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

[0158] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present invention, the computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.

[0159] The embodiment of the present invention also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method for predicting deformation of the supporting structure of the foundation pit around dense buildings provided by the embodiment of the present invention.

[0160] The computer program executes the above functions defined in the system / device of the embodiment of the present invention when it is executed by the processor 701. According to the embodiment of the present invention, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0161] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 709, and / or installed from the removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0162] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above functions defined in the system of the embodiment of the present invention are performed. According to the embodiment of the present invention, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0163] According to an embodiment of the present invention, the program code for executing the computer program provided by the embodiment of the present invention can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0164] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. 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 above-mentioned module, program segment, or a part of a 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 or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0165] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present invention may be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features described in the various embodiments of the present invention may be combined and / or combined in various ways. All of these combinations and / or combinations fall within the scope of the present invention.

[0166] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although each embodiment is described above, it does not mean that the measures in each embodiment cannot be used in combination advantageously. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A method for predicting deformation of supporting structures of foundation pits around densely populated buildings, characterized in that: The method comprises: Acquire excavation information of a foundation pit and soil information, support structure information, and hydrological information corresponding to the foundation pit, wherein the support structure information is determined based on dense building information around the foundation pit, and the support structure information includes vertical support information, horizontal support information, and inertia information of multiple points with different depths; Inputting the excavation information, the soil information, the vertical support information, the horizontal support information, the inertial information and the hydrological information into a deformation prediction model, and outputting an initial prediction result, wherein the initial prediction result includes a plurality of horizontal deformation information, deformation peak values ​​and deformation types, and the horizontal deformation information represents the horizontal deformation results of a plurality of points in the support structure; and Determine a target prediction result corresponding to the foundation pit based on a plurality of the horizontal deformation information, the deformation peak value and the deformation type, wherein the deformation type includes a cantilever type, a kicking type and an inward convex type, wherein the cantilever type indicates that the deformation curve of the support structure along the depth direction is a cantilever displacement deformation, the kicking type indicates that the deformation curve of the support structure along the depth direction is a kicking displacement deformation, and the inward convex type indicates that the deformation curve of the support structure along the depth direction is an inward convex displacement deformation, the support structure information also includes a buried depth value, and the buried depth value indicates the total length of the support structure in the depth direction of the foundation pit, the target prediction result includes a first deformation result corresponding to the cantilever type, a second deformation result corresponding to the kicking type, and a third deformation result corresponding to the inward convex type, and the excavation information includes a foundation pit depth value; Wherein, determining a target prediction result corresponding to the foundation pit based on the plurality of horizontal deformation information, the deformation peak value and the deformation type includes: Obtain a point depth value corresponding to each of the plurality of horizontal deformation information; when the deformation type is the cantilever type, determine the first deformation result based on the point depth value, the horizontal deformation information, the deformation peak value and the buried depth value; or, when the deformation type is the kicking type, determine the second deformation result based on the buried depth value, the point depth value and the deformation peak value; or, when the deformation type is the convex type, compare the point depth value with the foundation pit depth value and the buried depth value to obtain a comparison result; determine the third deformation result based on the comparison result, the deformation peak value, the buried depth value, the foundation pit depth value and the point depth value.

2. The prediction method according to claim 1, characterized in that: The excavation information includes excavation width information and excavation depth information, and the soil information includes strength information, stress information, deformation modulus information and physical information; The step of inputting the excavation information, the soil information, the vertical support information, the horizontal support information, the inertial information and the hydrological information into a deformation prediction model and outputting an initial prediction result includes: The excavation width information, the excavation depth information, the strength information, the stress information, the deformation modulus information, the physical information, the vertical support information, the horizontal support information, the inertial information and the hydrological information are input into the deformation prediction model to obtain a plurality of horizontal deformation information, the deformation peak value and the deformation type.

3. The prediction method according to claim 1, characterized in that: The method further comprises: The deformation type is determined based on depth information of a target point corresponding to the deformation peak among the plurality of points.

4. The prediction method according to claim 1, characterized in that: The determining the third deformation result based on the comparison result, the buried depth value, the foundation pit depth value and the point depth value comprises: In a case where the comparison result indicates that the point depth value is less than or equal to the foundation pit depth value, determining the third deformation result based on the deformation peak value, the foundation pit depth value and the point depth value; and When the comparison result indicates that the point depth value is greater than the foundation pit depth value and less than or equal to the burial depth value, the third deformation result is determined based on the deformation peak value, the foundation pit depth value, the point depth value and the burial depth value.

5. The prediction method according to any one of claims 1 to 4, characterized in that: The deformation prediction model is trained by the following operations: Acquire sample excavation information of a sample foundation pit and sample soil information, sample support structure information and sample hydrological information corresponding to the sample foundation pit, wherein the sample support structure information is determined based on dense building information around the sample foundation pit, and the sample support structure information includes sample vertical support information, sample horizontal support information and sample inertia information; and The sample excavation information, the sample soil information, the sample vertical support information, the sample horizontal support information, the sample inertia information and the sample hydrological information as well as their respective corresponding labels are used to train an initial deformation prediction model to obtain the deformation prediction model.

6. The prediction method according to claim 5, characterized in that: The deformation prediction model includes a plurality of target parameters; The target parameters are updated by the following operations: Determine an initial population and an objective function corresponding to initial parameters of the initial deformation prediction model, wherein the initial population includes a plurality of individuals, the individuals represent initial parameters, and the objective function is obtained based on monitoring values ​​and prediction values ​​corresponding to the sample foundation pit; updating the initial position information of the initial population based on the first updating strategy and the objective function to obtain intermediate position information; and The intermediate position information is cyclically updated based on the second update strategy, the update step size and the position information of the target individual until a preset stop strategy is met to obtain the target parameter, wherein the preset stop strategy includes at least one of the following: the rate of change of the objective function is less than a preset threshold and the number of iterations reaches a preset threshold.

7. A device for predicting deformation of supporting structures of foundation pits around densely populated buildings, characterized in that: The device comprises: An information acquisition module, used to acquire excavation information of a foundation pit and soil information, support structure information and hydrological information corresponding to the foundation pit, wherein the support structure information is determined based on dense building information around the foundation pit, including vertical support information, horizontal support information and inertia information; an initial prediction result output module, used for inputting the excavation information, the soil information, the vertical support information, the horizontal support information, the inertial information and the hydrological information into a deformation prediction model, and outputting an initial prediction result, wherein the initial prediction result includes a plurality of horizontal deformation information, deformation peak values ​​and deformation types, and the horizontal deformation information represents the horizontal deformation results of a plurality of points in the support structure; and a target prediction result determination module, for determining a target prediction result corresponding to the foundation pit based on the plurality of horizontal deformation information, the deformation peak value and the deformation type, the deformation type comprising a cantilever type, a kicking type and an inward convex type, the cantilever type characterizing that the deformation curve of the support structure along the depth direction is a cantilever displacement deformation, the kicking type characterizing that the deformation curve of the support structure along the depth direction is a kicking displacement deformation, the inward convex type characterizing that the deformation curve of the support structure along the depth direction is an inward convex displacement deformation, the support structure information further comprising a buried depth value, the buried depth value characterizing the total length of the support structure in the depth direction of the foundation pit, the target prediction result comprising a first deformation result corresponding to the cantilever type, a second deformation result corresponding to the kicking type, and a third deformation result corresponding to the inward convex type, and the excavation information comprising a foundation pit depth value; Among them, the target prediction result determination module includes: a depth value acquisition submodule, for acquiring the point depth value corresponding to each of the plurality of horizontal deformation information; a first deformation result determination submodule, for determining the first deformation result based on the point depth value, the horizontal deformation information, the deformation peak value and the buried depth value when the deformation type is the cantilever type; or, a second deformation result determination submodule, for determining the second deformation result based on the buried depth value, the point depth value and the deformation peak value when the deformation type is the kicking type; or, a depth value comparison submodule, for comparing the point depth value with the foundation pit depth value and the buried depth value to obtain a comparison result when the deformation type is the inward convex type; and a third deformation result determination submodule, for determining the third deformation result based on the comparison result, the deformation peak value, the buried depth value, the foundation pit depth value and the point depth value.

Images