Deformation calculation method for shield underneath passing existing tunnel structure based on deep learning

Abstract

The invention discloses a deep learning-based deformation calculation method for a shield under-crossing existing tunnel structure, and belongs to the technical field of tunnel engineering pile foundation underpinning. The method comprises the following steps: establishing a deep learning prediction model to obtain ground surface settlement caused by a new shield tunnel; the stratum loss rate is obtained through inversion according to a Loganthan-Poulos ground surface settlement analysis formula; calculating the displacement of the soil body at the buried depth of the existing tunnel; calculating the longitudinal additional load of the existing tunnel structure; calculating the longitudinal equivalent flexural rigidity and equivalent shear rigidity of the existing tunnel structure; and calculating the vertical displacement on the axis of the existing tunnel structure under the action of the additional load, and calculating the longitudinal deformation of the tunnel structure under the additional load. According to the method, the problem that the stratum loss rate is difficult to determine due to stratum difference can be effectively solved, and the ground surface settlement value caused by shield construction and the soil displacement at the buried depth of the existing tunnel can be rapidly and accurately obtained.

Description

Technical Field

[0001] The present invention belongs to the technical field of tunnel engineering, and specifically relates to a method for calculating the deformation of a shield machine passing through an existing tunnel structure based on deep learning. Background Art

[0002] With the gradual development of urban underground space, various types of tunnels are densely distributed in underground space, and the number of new shield tunnels passing under existing tunnels is increasing. The construction of new shield tunnels will inevitably disturb the surrounding soil, causing soil deformation within a certain range. When a new shield tunnel passes under an existing tunnel, the existing tunnel structure will deform under the additional load caused by the deformation of the surrounding soil, which will have an adverse effect on the service status of the existing tunnel, such as cracking of the pipe segments and damage of bolts, thereby threatening the operational safety of the existing tunnel. Therefore, estimating the longitudinal deformation of the existing tunnel structure under which the new shield tunnel passes can effectively ensure safety issues during construction.

[0003] At present, the impact of new shield tunnel projects on the longitudinal deformation of existing tunnel structures is evaluated by theoretical analysis methods, mostly using a two-stage method: Stage 1, calculating the additional longitudinal load on the existing tunnel caused by the surface settlement of the new shield tunnel; Stage 2, calculating the longitudinal deformation of the existing tunnel structure under the additional load. In the calculation of surface settlement caused by the new shield tunnel, the value of the stratum loss rate is a key factor in whether the calculation result is accurate. The existing value selection method is usually based on previous shield construction experience, but due to the obvious differences in strata between different projects, the value of the stratum loss rate is difficult to determine, which leads to distortion in the calculation of the longitudinal deformation of the existing tunnel structure. Summary of the invention

[0004] The purpose of an embodiment of the present invention is to provide a method for calculating the deformation of a shield machine passing through an existing tunnel structure based on deep learning. The method predicts the surface settlement of the shield machine through an established deep learning model driven by both data and physics, and then calculates the stratum loss rate by inverting the predicted surface settlement value. The soil displacement at the burial depth of the existing tunnel is then calculated and applied as a displacement load to the existing tunnel assumed to be an elastic foundation beam. A simplified analysis of the interaction between the new shield tunnel, the soil body and the existing tunnel is performed in sequence, and the displacement of the existing tunnel under the action of the additional load is calculated, thereby effectively solving the problem of the difficulty in determining the stratum loss rate. The longitudinal deformation of the existing tunnel structure under which the new shield tunnel passes can be quickly and accurately calculated, providing a reference basis for quickly and accurately monitoring the safety of the existing tunnel, thereby solving at least one technical problem involved in the background technology.

[0005] In order to solve the above-mentioned technical problems, the present invention is achieved as follows:

[0006] In a first aspect, an embodiment of the present invention provides a method for calculating deformation of a shield tunnel under an existing tunnel structure based on deep learning, comprising the following steps:

[0007] Step S1, establishing a deep learning prediction model based on data-physics dual drive, inputting geometric parameters, formation parameters, excavation parameters and other parameters of the newly built shield tunnel into the model, and predicting the surface settlement caused by the newly built shield tunnel;

[0008] Step S2, inverting the predicted surface settlement through the Loganathan-Poulos surface settlement analytical formula to obtain the stratum loss rate caused by the excavation of the new shield tunnel;

[0009] Step S3, obtaining the soil displacement at the buried depth of the existing tunnel according to the semi-analytical solution and inversion of the displacement of the surrounding soil caused by tunnel excavation proposed by Loganathan-Poulos and the stratum loss rate;

[0010] Step S4, calculating the additional longitudinal load of the existing tunnel structure by using a displacement control method according to the soil displacement at the buried depth of the existing tunnel;

[0011] Step S5, calculating the longitudinal equivalent bending stiffness and equivalent shear stiffness of the existing tunnel structure;

[0012] Step S6, assuming that the existing tunnel is a Timoshenko beam resting on a Winkler foundation, the vertical displacement on the axis of the existing tunnel structure under the additional load is calculated according to the longitudinal additional load of the existing tunnel structure, and the longitudinal deformation of the tunnel structure under the additional load is calculated with the help of MATLAB.

[0013] In a second aspect, an embodiment of the present invention provides an electronic device, including:

[0014] at least one processor;

[0015] At least one memory for storing at least one program;

[0016] When the at least one program is executed by the at least one processor, the at least one processor implements the steps of the method described in the first aspect.

[0017] In a third aspect, an embodiment of the present invention provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0018] In a fourth aspect, an embodiment of the present invention provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] 1. Compared with the existing calculation method, the present invention predicts the shield surface settlement through the established data-physics dual-driven deep learning model, and then calculates the stratum loss rate through inversion of the predicted surface settlement value, and then calculates the soil displacement at the depth of the existing tunnel and applies it as a displacement load on the existing tunnel assumed to be an elastic foundation beam, and then performs simplified new shield tunnel-soil-existing tunnel interaction analysis in turn, and calculates the displacement of the existing tunnel under the action of additional load, which can effectively solve the problem that the stratum loss rate is difficult to determine due to stratum differences, and quickly and accurately obtains the surface settlement value caused by shield construction and the soil displacement at the depth of the existing tunnel, thereby calculating the additional load acting on the existing tunnel caused by the soil displacement and the longitudinal deformation of the existing tunnel under the load.

[0021] 2. The present invention can provide certain theoretical support and practical experience for the prediction, analysis and control of the longitudinal deformation of existing tunnels in new shield tunnel projects, and has certain reference value for ensuring the safety of existing tunnel operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0023] Figure 1 It is a flow chart of a method for calculating deformation of a shield tunnel under an existing tunnel structure based on deep learning provided by the present invention;

[0024] Figure 2 It is a schematic diagram of the impact of the construction of a new shield tunnel provided by the present invention on the existing tunnel structure;

[0025] Figure 3 It is a diagram of a longitudinal Timoshenko beam model of a tunnel on a Winkler foundation provided by the present invention;

[0026] Figure 4 It is one of the hardware structure diagrams of the electronic device provided by the present invention;

[0027] Figure 5 This is the second schematic diagram of the hardware structure of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] The terms "first", "second", etc. in the specification and claims of the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0030] In conjunction with the accompanying drawings, the method for calculating the deformation of a shield machine passing through an existing tunnel structure based on deep learning provided by an embodiment of the present invention is described in detail below through specific embodiments and their application scenarios.

[0031] See also Figure 1 As shown, an embodiment of the present invention provides a method for calculating the deformation of a shield tunnel under an existing tunnel structure based on deep learning, comprising the following steps:

[0032] Step S1, establishing a deep learning prediction model based on data-physics dual drive, inputting geometric parameters, formation parameters, excavation parameters and other parameters of the newly built shield tunnel into the model, and predicting the surface settlement caused by the newly built shield tunnel;

[0033] Step S2, inverting the predicted surface settlement through the Loganathan-Poulos surface settlement analytical formula to obtain the stratum loss rate caused by the excavation of the new shield tunnel;

[0034] Step S3, obtaining the soil displacement at the buried depth of the existing tunnel according to the semi-analytical solution and inversion of the displacement of the surrounding soil caused by tunnel excavation proposed by Loganathan-Poulos and the stratum loss rate;

[0035] Step S4, calculating the additional longitudinal load of the existing tunnel structure by using a displacement control method according to the soil displacement at the buried depth of the existing tunnel;

[0036] Step S5, calculating the longitudinal equivalent bending stiffness and equivalent shear stiffness of the existing tunnel structure;

[0037] Step S6, combining Figure 2 and Figure 3 As shown, assuming that the existing tunnel 3 is a Timoshenko beam placed on the Winkler foundation 4, the vertical displacement of the existing tunnel structure axis 1 under the additional load is calculated according to the longitudinal additional load of the existing tunnel structure, and the longitudinal deformation of the tunnel structure 2 under the additional load is calculated with the help of MATLAB.

[0038] In step S1, it should be noted that the tunnel geometry parameter is the tunnel burial depth; the formation parameters include the refined representation of the soil above the tunnel and the soil at the tunnel face rich in spatial physical information, as well as the groundwater burial depth; the excavation parameters include the total thrust, cutter head torque, cutter head speed, propulsion speed and soil bin pressure; other parameters include whether the shield machine is shut down.

[0039] In step S2, the ground loss rate w caused by the excavation of the new shield tunnel is s (x) is calculated by the following formula:

[0040]

[0041] Where ε is the formation loss rate; ν is the Poisson's ratio of the soil; z 0 is the burial depth of the new shield tunnel; D is the outer diameter of the new shield tunnel structure, in meters.

[0042] In step S3, the soil displacement u(x) at the existing tunnel burial depth is calculated by the following formula:

[0043]

[0044] Where h is the existing tunnel depth.

[0045] In step S4, the additional load q(x) on the axis of the existing tunnel structure is calculated by the following formula:

[0046] q(x)=kD e u(x)

[0047] Where k is the foundation reaction coefficient, unit kN / m 3 ;D e It is the outer diameter of the existing tunnel structure, in meters.

[0048] In step S5, the longitudinal equivalent bending stiffness (EI)′ of the existing tunnel structure is calculated by the following formula:

[0049] (EI)′=ηE c I

[0050] Where η is the longitudinal bending stiffness correction factor; E c is the elastic modulus of concrete, in kPa; I is the moment of inertia of the segment cross section, in m 4 .

[0051] The longitudinal equivalent shear stiffness (κGA)′ of the existing tunnel structure is calculated by the following formula:

[0052]

[0053] Where ξ is the longitudinal shear stiffness correction factor; b is the longitudinal bolt length, in m; l c is the segment width, in m; n is the number of longitudinal bolts; κ b is the Timoshenko shear coefficient of the longitudinal bolt; G b is the longitudinal bolt shear modulus, unit kPa; A b is the longitudinal bolt cross-sectional area, in m 2 κ c is the Timoshenko shear coefficient of the segment ring; G c is the shear modulus of concrete, unit is kPa; A c is the cross-sectional area of ​​the tunnel, in m 2 , and A c =πtD, t is the thickness of the segment, unit: m.

[0054] In step S6, the calculation method of the vertical displacement of the existing tunnel structure under the additional load is as follows:

[0055] By Fourier expansion of the longitudinal additional load q(x) of the existing tunnel structure, we can obtain:

[0056]

[0057] In the formula,

[0058] Substituting the following control equation into the vertical displacement of the existing tunnel structure under the additional load can be obtained:

[0059]

[0060] Where u(x) is the displacement of the soil at the depth of the existing tunnel, in m; q(x) is the additional load on the axis of the existing tunnel structure, in kN / m; (EI)′ is the longitudinal equivalent bending stiffness of the existing tunnel structure, in kN·m 2 ; (κGA)′ is the longitudinal equivalent shear stiffness of the existing tunnel structure, unit: kN.

[0061] The control equation solution is divided into two working conditions:

[0062] (1) When kD e <4(κGA)′ 2 / (EI)′:

[0063]

[0064] Where:

[0065]

[0066]

[0067] (2) When kD e ≥4(κGA)′ 2 / (EI)′:

[0068]

[0069] Where:

[0070]

[0071] In the formula, the unknown coefficient c 1 ,c 2 ,c 3 ,c 4 Obtained according to different boundary conditions;

[0072] Assuming that both ends of the tunnel are free ends, the bending moment and shear force of the existing tunnel at the boundary of the calculation range are both 0, and the boundary conditions can be written as:

[0073]

[0074]

[0075] In the formula, the tunnel turning angle ψ(x) is expressed as follows:

[0076]

[0077] With the help of MATLAB calculation method, the longitudinal deformation of the tunnel structure under additional load can be solved.

[0078] like Figure 4 As shown, an embodiment of the present invention further provides an electronic device 600, which includes a processor 601, a memory 602, and a program or instruction stored in the memory 602 and executable on the processor 601. When the program or instruction is executed by the processor 601, each process of the above-mentioned 3DGS-based panoramic reconstruction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0079] It should be noted that the first electronic device in the embodiment of the present invention includes the mobile electronic device and the non-mobile electronic device mentioned above.

[0080] Figure 5The present invention is a schematic diagram of the hardware structure of an electronic device.

[0081] The electronic device 700 includes but is not limited to: a radio frequency unit 701, a network module 702, an audio output unit 703, an input unit 704, a sensor 705, a display unit 706, a user input unit 707, an interface unit 708, a memory 709, and a processor 710.

[0082] Those skilled in the art will appreciate that the electronic device 700 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 710 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 5 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0083] It should be understood that in the embodiment of the present invention, the input unit 704 may include a graphics processor (Graphics Processing Unit, GPU) 7041 and a microphone 7042, and the graphics processor 7041 processes the image data of the static image or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 706 may include a display panel 7061, and the display panel 7061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 707 includes a touch panel 7071 and other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include two parts: a touch detection device and a touch controller. Other input devices 7072 may include but are not limited to a physical keyboard, a function key (such as a volume control button, a switch button, etc.), a trackball, a mouse, and a joystick, which will not be repeated here. The memory 709 can be used to store software programs and various data, including but not limited to applications and operating systems. The processor 710 can integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and applications, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 710.

[0084] An embodiment of the present invention further provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned 3DGS-based panoramic reconstruction method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0085] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0086] An embodiment of the present invention further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned 3DGS-based panoramic reconstruction method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0087] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0088] In addition, it should be noted that the scope of the methods and devices in the embodiments of the present invention is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

[0089] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A method for calculating the deformation of a shield tunnel under an existing tunnel structure based on deep learning, characterized in that: The following steps are involved: Step S1, establishing a deep learning prediction model based on data-physics dual drive, inputting geometric parameters, formation parameters, excavation parameters and other parameters of the newly built shield tunnel into the model, and predicting the surface settlement caused by the newly built shield tunnel; Step S2, inverting the predicted surface settlement through the Loganathan-Poulos surface settlement analytical formula to obtain the stratum loss rate caused by the excavation of the new shield tunnel; Step S3, obtaining the soil displacement at the buried depth of the existing tunnel according to the semi-analytical solution and inversion of the displacement of the surrounding soil caused by tunnel excavation to obtain the stratum loss rate; Step S4, calculating the additional longitudinal load of the existing tunnel structure by using a displacement control method according to the soil displacement at the buried depth of the existing tunnel; Step S5, calculating the longitudinal equivalent bending stiffness and equivalent shear stiffness of the existing tunnel structure; Step S6, assuming that the existing tunnel is a Timoshenko beam resting on a Winkler foundation, the vertical displacement on the axis of the existing tunnel structure under the additional load is calculated according to the longitudinal additional load of the existing tunnel structure, and the longitudinal deformation of the tunnel structure under the additional load is calculated with the help of MATLAB.

2. The method according to claim 1, characterized in that In step S1, the tunnel geometry parameter is the tunnel burial depth; the formation parameters include the refined representation of the soil above the tunnel and the soil at the tunnel face rich in spatial physical information, as well as the groundwater burial depth; the excavation parameters include the total thrust, cutter head torque, cutter head speed, propulsion speed and soil bin pressure; other parameters include whether the shield machine is shut down.

3. The method according to claim 2, characterized in that In step S2, the ground loss rate w caused by the excavation of the new shield tunnel is s (x) is calculated by the following formula: Where ε is the stratum loss rate; ν is the Poisson's ratio of the soil; z0 is the burial depth of the new shield tunnel; and D is the outer diameter of the new shield tunnel structure.

4. The method according to claim 3, characterized in that In step S3, the soil displacement u(x) at the existing tunnel burial depth is calculated by the following formula: Where h is the existing tunnel depth.

5. The method according to claim 4, characterized in that In step S4, the longitudinal additional load q(x) of the existing tunnel structure is calculated by the following formula: q(x)=kD e u(x) Where k is the foundation reaction coefficient; D e It is the outer diameter of the existing tunnel structure.

6. The method according to claim 5, characterized in that In step S5, the longitudinal equivalent bending stiffness (EI)′ of the existing tunnel structure is calculated by the following formula: (EI)′=ηE c I Where η is the longitudinal bending stiffness correction factor; E c is the elastic modulus of concrete; I is the moment of inertia of the segment cross section.

7. The method according to claim 6, characterized in that In step S5, the longitudinal equivalent shear stiffness (κGA)′ of the existing tunnel structure is calculated by the following formula: Where ξ is the longitudinal shear stiffness correction factor; l b is the longitudinal bolt length; l c is the segment ring width; n is the number of longitudinal bolts; κ b is the Timoshenko shear coefficient of the longitudinal bolt; G b is the longitudinal bolt shear modulus; A b is the longitudinal bolt cross-sectional area; κ c is the Timoshenko shear coefficient of the segment ring; G c is the shear modulus of concrete; A c is the cross-sectional area of ​​the tunnel, and A c =πtD, t is the thickness of the segment.

8. The method according to claim 1, characterized in that In step S6, the calculation method of the vertical displacement under the additional load on the axis of the existing tunnel structure is as follows: By Fourier expansion of the additional load q(x) on the axis of the existing tunnel structure, we can obtain: In the formula, Substituting the following control equation into the vertical displacement of the existing tunnel structure under the additional load can be obtained:

9. The method according to claim 8, characterized in that The control equation solution is divided into two working conditions: (1) When kD e <4(κGA)′ 2 / (EI)′: Where: (2) When kD e ≥4(κGA)′ 2 / (EI)′: Where: In the formula, the unknown coefficients c1, c2, c3, c4 are obtained according to different boundary conditions; Assuming that both ends of the tunnel are free ends, the bending moment and shear force of the existing tunnel at the boundary of the calculation range are both 0, and the boundary conditions are: In the formula, the tunnel turning angle ψ(x) is expressed as follows: With the help of MATLAB calculation method, the longitudinal deformation of the tunnel structure under additional load can be solved.

Images