Joint regulation method for ground surface settlement and pile foundation deformation of shield tunneling under buildings

Abstract

The application discloses a method for jointly regulating ground surface settlement and pile foundation deformation during shield tunneling under buildings, and relates to the field of settlement and deformation regulation. The application establishes a mapping model of ground surface settlement and pile foundation deformation based on historical multidimensional data, so that key deformation parameters in the construction process can be accurately predicted and evaluated. Through the mapping model driven by historical reinforcement data, combined with current tunnel and pile foundation parameters and preset grouting parameters, intelligent reinforcement width calculation and operation of soft strata are realized, and the scientificity and efficiency of reinforcement are improved. Then, through setting a standard interval to dynamically monitor key parameters, combined with the collaborative feedback mechanism of the mapping model and the prediction model, automatic adjustment and optimization of construction parameters are realized, ensuring that the construction process is always within a safe and controllable range. Thus, the adaptability and safety of shield construction are significantly enhanced, and the construction risk caused by complex geological conditions or improper parameter setting is effectively reduced.

Description

Technical Field

[0001] This invention belongs to the field of settlement and deformation control, and specifically relates to a method for the joint control of surface settlement and pile foundation deformation when a shield tunnel passes under a building. Background Technology

[0002] Currently, the accuracy of predicting stratum deformation under complex geological conditions is not high, making it difficult to accurately assess the impact of construction on existing structures; the reinforcement of weak strata lacks scientific basis, and the reinforcement scope and parameter settings often rely on experience, resulting in unstable reinforcement effects or waste of resources; the adjustment of key control parameters (such as grouting pressure, jack thrust, etc.) during construction is lagging behind, making dynamic optimization impossible, which can easily lead to excessive surface settlement or excessive deformation of building pile foundations. Summary of the Invention

[0003] In response to the problems in related technologies, this invention proposes a method for the joint control of surface settlement and pile foundation deformation when a shield tunnel passes under a building, so as to overcome the above-mentioned technical problems existing in the existing related technologies.

[0004] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution: This invention provides a method for jointly controlling surface settlement and pile foundation deformation when a shield tunnel passes under a building, comprising the following steps: S1. Set several types of settlement and deformation influencing factors and obtain the current data on the stratum type, tunnel depth and pile distribution of the building under which the shield tunnel passes; S2. Based on the settlement deformation influencing factor type in S1, obtain the current corresponding settlement deformation influencing factor data, and construct the current final shield tunneling under building model based on this. S3. Collect multi-dimensional historical data and establish a mapping model for surface settlement and pile foundation deformation. S4. Collect historical reinforcement data to construct a mapping model, then collect the current tunnel and pile foundation parameters and preset grouting parameters and input them into the mapping model in S4 to obtain the left and right and up and down reinforcement widths of the tunnel when the shield tunnel passes through the soft stratum and carry out reinforcement operations. S5. Set the standard range for several sets of parameters, including surface settlement and pile foundation deformation. Based on the reinforcement operation in S4, input the current multiple sets of parameters into the mapping model in S3 for mapping, and combine them with the prediction of the model in S2. If the mapped and predicted data are all within the corresponding standard range, no adjustment is needed; otherwise, repeatedly adjust the grouting pressure and jack thrust, remap and update the model parameters in S2 to re-predict until the standard requirements are met or S6 is executed. S6. Repeat the hardening operation in S4 and repeat S5 until all types of data remapped and re-predicted in S5 are within the corresponding specification range.

[0005] Preferably, step S1 includes the following steps: S11. Pre-acquire the type data of the strata being traversed, the tunnel depth data, and the type, depth, and distribution data of the building's pile foundations during the current shield tunneling process under the building, to obtain the current strata type data, the current tunnel depth data, and the current building pile foundation dataset; the strata type data includes silt, silty clay, and soft strata, etc. S12. Define several types of factors that affect ground settlement and pile foundation deformation during the shield tunneling process, and obtain a set of settlement and deformation influencing factor types; the set of settlement and deformation influencing factor types includes ground loss, soil pressure, water and soil pressure at the excavation face, grouting pressure, jack thrust, tunnel geometric parameters, and the interaction between the ground and the pile foundation, etc. By acquiring data on the geological strata type, tunnel depth, and the type, depth, and distribution of building piles in the area where the shield tunnel passes under a building in advance, accurate basic geological and structural information can be provided for subsequent construction. This significantly improves the reliability of the settlement and deformation prediction model and avoids misjudgments due to missing data.

[0006] Preferably, step S2 includes the following steps: S21. Based on the set of settlement deformation influencing factors, obtain the initial data of various settlement deformation influencing factors corresponding to the current shield tunneling process under the building, and obtain the current initial settlement deformation influencing factor dataset. S22. Based on the current initial settlement deformation influencing factor dataset, current stratum type data, current tunnel depth data, and current building pile foundation dataset, and combined with the actual engineering situation, construct a three-dimensional numerical model corresponding to the current shield tunneling under the building process, and obtain the current final shield tunneling under the building model. By integrating initial data on settlement and deformation influencing factors, data on strata types, tunnel depth data, and building pile foundation datasets, and closely combining them with engineering practice, a three-dimensional numerical model is constructed. This model enables refined simulation of the shield tunneling process under buildings, significantly improving the prediction accuracy of strata response and structural deformation. The model can comprehensively reflect the combined influence of key factors such as strata loss, construction parameters, tunnel geometric parameters, and the interaction between strata and pile foundations, providing a scientific basis for optimizing construction plans.

[0007] Preferably, step S3 includes the following steps: S31. Based on the ground loss, grouting pressure, jack thrust, and tunnel geometric parameters in the aforementioned set of factors affecting settlement and deformation, obtain the pile foundation data, ground type data, grouting pressure data, left-right thrust ratio and up-down thrust ratio data of the jacks, tunnel parameter data, and corresponding ground loss data, soil pressure, excavation face water and soil pressure, surface settlement data, and pile foundation deformation data from several historical shield tunneling processes under buildings. This yields historical grouting pressure datasets, historical left-right thrust ratio datasets, historical up-down thrust ratio datasets, historical tunnel geometric parameter datasets, historical ground loss datasets, historical soil pressure datasets, historical excavation face water and soil pressure datasets, historical surface settlement datasets, and historical pile foundation deformation datasets. S32. Based on the historical data collected in S31, construct a mapping model with the inputs of pile foundation data, stratum type data, grouting pressure data, jack left-right thrust ratio data, jack up-down thrust ratio data, tunnel parameter data, and the outputs of stratum loss data, soil pressure data, excavation face water and soil pressure data, surface settlement data, and pile foundation deformation data, to obtain the final pressure-settlement deformation mapping model. The construction of this mapping model enables intelligent prediction of everything from construction control parameters to settlement and deformation response, significantly improving the predictive ability and risk control level of the construction process. Through model training driven by historical data, it can effectively identify the nonlinear relationships and coupling effects among various influencing factors, providing scientific guidance for the optimization and adjustment of construction parameters. In addition, the final pressure-settlement deformation mapping model is mutually verified and coordinated with the current final shield tunneling building model, thereby further improving the accuracy of subsequent predictions of surface settlement and pile deformation.

[0008] Preferably, step S4 includes the following steps: S41. Based on the stratum type described in S1, obtain the stratum type data, tunnel left and right and up and down reinforcement width, tunnel parameters, grouting parameters and pile foundation parameters corresponding to several historical stratum reinforcement operations for weak strata before shield tunneling under buildings, and obtain historical stratum type data before reinforcement, historical tunnel parameter set, historical grouting parameter set, historical pile foundation parameter set, historical left and right reinforcement width dataset and historical up and down reinforcement width dataset. S42. Based on the historical data collected in S41, construct a mapping model with the input of the stratum type data before reinforcement, the tunnel parameter set, the grouting parameters, and the pile foundation parameters, and the output of the left and right and up and down reinforcement width data of the tunnel, to obtain the final tunnel reinforcement width mapping model. S43. Collect the tunnel parameter data and pile parameter data corresponding to the current shield tunneling process under the building, and obtain the preset grouting parameter data to obtain the current tunnel parameter dataset, the current pile parameter dataset and the current preset grouting parameter dataset. If the current stratum type data is a weak stratum, the current stratum type data, the current tunnel parameter dataset, the current pile parameter dataset, and the current preset grouting parameter dataset are input into the final tunnel reinforcement width mapping model for mapping to obtain the current left and right reinforcement width dataset and the current up and down reinforcement width dataset; otherwise, no grouting reinforcement operation is required. Then, based on the current left and right reinforcement width dataset, the current up and down reinforcement width dataset, and the current preset grouting parameter dataset, grouting reinforcement operations are performed on the left and right sides and up and down of the tunnel in the corresponding strata before the current shield tunnel passes under the building. After the operation is completed, the current stratum type data is updated to the current stratum type data after reinforcement. By automatically analyzing the complex nonlinear relationship between the reinforcement width and multiple factors such as the type of stratum, tunnel depth, grouting parameters, and pile characteristics before reinforcement using machine learning models, the problem of insufficient or excessive reinforcement that may be caused by traditional empirical formulas or simple analogies is avoided. This effectively controls construction costs and ensures reinforcement effect, minimizes the disturbance of the surrounding soft strata caused by tunnel excavation, significantly reduces the risk of surface settlement and building deformation, and ensures the safety of existing structures and the stability of the construction process.

[0009] Preferably, step S5 includes the following steps: S51. Based on the current engineering requirements for shield tunneling under buildings, obtain the standard range of current ground loss, soil pressure, excavation face water and soil pressure, surface settlement data, and pile foundation deformation data. S52. Input the current pile parameter dataset, the current tunnel parameter dataset, the current reinforced stratum type data, the current preset grouting pressure data, and the current preset left-right thrust ratio and up-down thrust ratio data of the jacks into the final pressure-settlement deformation mapping model for mapping to obtain the current initial stratum loss data, the current initial soil chamber pressure data, the current initial excavation face water and soil pressure data, the current initial surface settlement data, and the current initial pile foundation deformation data. Based on S51 and the predictions of the current final shield tunneling model, if the current initial ground loss data, current initial soil pressure data, current initial excavation face water and soil pressure data, current initial surface settlement data, and current initial pile foundation deformation data, and all the prediction data of the current final shield tunneling model are within the corresponding specification range, no adjustment is required; otherwise, execute S53. S53. Set a first repetition threshold; repeatedly adjust the current preset grouting pressure data, the current preset left-right thrust ratio of the jack, and the current preset up-down thrust ratio data. In each repetition, the adjusted current preset grouting pressure data, the current preset left-right thrust ratio of the jack, and the current preset up-down thrust ratio data are combined with the current pile parameter dataset, the current tunnel parameter dataset, and the current reinforced stratum type data and input again into the final pressure-settlement deformation mapping model for mapping and the parameters of the current final shield tunneling building model are reset. If the number of repetitions is less than or equal to the first repetition threshold, and all types of mapping data in the mapping results and all types of prediction data in the current final shield tunneling building model are within the corresponding specification range, the adjustment is complete; otherwise, proceed to S6. By constructing an intelligent parameter adjustment mechanism based on standard interval constraints, the key control indicators during shield tunneling under buildings can be automatically verified and dynamically optimized, significantly improving the safety and reliability of the construction process. By establishing a multi-dimensional data mapping relationship, the construction parameters and predicted deformation responses can be correlated and compared in real time, effectively avoiding parameter setting deviations that may be caused by traditional experience or single mapping models, ensuring that all key indicators are always within the safe range allowed by engineering specifications.

[0010] Preferably, step S6 includes the following steps: S61. Repeat the grouting operation in S43 on the left, right and up and down of the tunnel in the corresponding stratum before the current shield tunnel passes under the building. After the operation is completed, update and obtain the current reinforced stratum type data again, and repeat S52 and S53 until the number of repetitions in S53 is less than or equal to the first repetition threshold, and all kinds of mapping data in the mapping results and all kinds of prediction data of the current final shield tunnel under the building model are within the corresponding specification range. By repeatedly performing grouting reinforcement operations and continuously updating the stratum condition data, a closed-loop feedback control system is formed, which effectively solves the problem that simply adjusting the grouting pressure data and the left-right thrust ratio and up-down thrust ratio of the jacks is insufficient to meet the construction control requirements under complex geological conditions. By prioritizing the adjustment of the grouting pressure data and the left-right thrust ratio and up-down thrust ratio of the jacks, and then repeating the grouting reinforcement operation, the operation progresses from easy to difficult, maximizing the efficiency of surface settlement and building pile foundation deformation control.

[0011] The joint control system for surface settlement and pile foundation deformation of shield tunneling under buildings includes a basic data acquisition module, a shield model construction module, a deformation mapping model construction module, a reinforcement data mapping module, a first adjustment module, and a second adjustment module. The basic data acquisition module is used to acquire data on the stratum type, tunnel depth, and pile foundation distribution of the building currently being tunneled under by the shield tunnel. The shield tunneling model building module is used to build the final shield tunneling model of the building. The deformation mapping model construction module is used to establish a mapping model for surface settlement and pile foundation deformation. The reinforcement data mapping module is used to map the left and right and up and down reinforcement widths of the tunnel when the shield tunnel passes under the soft strata and to perform reinforcement operations. The first adjustment module is used to repeatedly adjust the grouting pressure and the jack thrust. The second adjustment module is used to repeat the reinforcement operation and adjust the grouting pressure and jack thrust.

[0012] The present invention has the following beneficial effects: 1. This invention constructs a multi-dimensional analysis and control system for the entire process of shield tunneling under buildings, achieving accurate prediction and effective control of construction risks under complex geological conditions. Specifically, a mapping model of surface settlement and pile foundation deformation based on historical multi-dimensional data enables accurate prediction and assessment of key deformation parameters during construction. Furthermore, a mapping model driven by historical reinforcement data, combined with current tunnel and pile foundation parameters and preset grouting parameters, enables intelligent calculation and operation of reinforcement width for soft strata, improving the scientific rigor and efficiency of reinforcement. By setting standardized intervals for dynamic monitoring of key parameters, and combining the collaborative feedback mechanism of the mapping and prediction models, automatic adjustment and optimization of construction parameters are achieved, ensuring that the construction process remains within a safe and controllable range. This significantly enhances the adaptability and safety of shield tunneling and effectively reduces construction risks caused by complex geological conditions or improper parameter settings.

[0013] 2. In this invention, a machine learning model is used to automatically analyze the complex nonlinear relationship between multiple factors such as the type of stratum, tunnel depth, grouting parameters, and pile characteristics before reinforcement and the reinforcement width. This avoids the problems of insufficient or excessive reinforcement that may be caused by traditional empirical formulas or simple analogies, thereby effectively controlling construction costs and ensuring reinforcement effect.

[0014] 3. In this invention, by repeatedly performing grouting reinforcement operations and continuously updating the formation state data, a closed-loop feedback control system is formed, which effectively solves the problem that it is difficult to meet the construction control requirements under complex geological conditions by simply adjusting the grouting pressure data, the left-right thrust ratio of the jack, and the up-down thrust ratio parameters.

[0015] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the method for joint control of surface settlement and pile foundation deformation when a shield tunnel passes under a building, as per the present invention. Figure 2 A schematic diagram illustrating the process of constructing the final shield tunneling model for this invention; Figure 3 A schematic diagram of the process for constructing the final pressure-settlement deformation mapping model for this invention; Figure 4 This is a schematic diagram illustrating the process of mapping current grouting reinforcement data in this invention. Figure 5 This is a schematic diagram of the process of repeatedly adjusting the grouting pressure and the jack thrust of the present invention; Figure 6 This is a line graph showing the changing trends of key parameters during the shield tunneling process of this invention. From top to bottom, the graph shows the changes in ground loss with shield tunneling distance, soil pressure with shield tunneling distance, excavation face water and soil pressure with shield tunneling distance, surface settlement with shield tunneling distance, and pile foundation deformation with shield tunneling distance. Figure 7 This is a schematic diagram of the process of repeatedly grouting and reinforcing the current stratum according to the present invention. Detailed Implementation

[0018] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0020] Example 1 Please see Figure 1 This embodiment describes a method for jointly controlling surface settlement and pile foundation deformation when a shield tunnel passes under a building, including the following steps: S1. Set several types of settlement and deformation influencing factors and obtain the current data on the stratum type, tunnel depth and pile distribution of the building under which the shield tunnel passes; Please see Figure 2 S1 includes the following steps: S11. Pre-acquire the type data of the strata being traversed, the tunnel depth data, and the type, depth, and distribution data of the building's pile foundations during the current shield tunneling process under the building, to obtain the current strata type data, the current tunnel depth data, and the current building pile foundation dataset; the strata type data includes silt, silty clay, and soft strata, etc. For example, as follows: 1. Obtain the type data of the strata traversed: The strata within the main traversal and influence area of ​​the shield tunnel are divided into four layers according to engineering geological units, as shown in Table 1 below: Table 1 Examples of Stratigraphic Types Traversed

[0021] According to Table 1, the current traversed strata type data is as follows: mainly soft strata with No. 1 and No. 2, and locally silty clay interlayers with No. 4. 2. Pre-acquire current tunnel depth data: The tunnel design axis burial depth (referring to the vertical distance from the tunnel arch to the natural ground) was measured at the following key section after departing from the HE2 station at Hengqin Port: the arch burial depth is 19.0 meters; the tunnel axis midpoint burial depth is 22.85 meters (considering a tunnel outer diameter of 7.7 meters, an arch burial depth of 19.0 meters, and a tunnel bottom burial depth of 26.7 meters); the overburden thickness in this section is either 19.0 m (arch) or 22.85 m (axis). 3. Pre-acquire data on the type, depth, and distribution of the current building's pile foundations: Building Structure: The inspection platform is a reinforced concrete frame structure, with the upper load transferred to the pile cap through the columns; the Lianhua Avenue ramp bridge is a prestressed concrete box girder bridge with column piers and bored piles for the foundation; Pile Type: All piles are bored piles with a concrete strength grade of C35; Pile Design Depth: The effective pile length (measured from the bottom of the pile cap) for the inspection platform is 25.0 meters, with the pile tip penetrating into the lower part of the No. 2 silty clay layer; The effective pile length for the piles under piers C3# and C4# of the Lianhua ramp bridge is 30.0 meters, with the pile tip penetrating the No. 2 soil layer and entering the No. 4 silty clay layer as the bearing layer; Pile Distribution (Plan and Section Data): Plan Distribution: The column spacing of the inspection platform is 5m×5m, with 4 piles arranged in a rectangle (2×2) under each pile cap, and the pile cap size is 2.5m×2.5m. The C3# pier of the Lianhua Ramp Bridge has two piles under its foundation, with a center-to-center distance of 4.5m; the C4# pier has four piles (arranged in a 2×2 pattern) under its foundation, with a longitudinal spacing of 3.5m and a transverse spacing of 4.0m. Cross-sectional positional relationship (with the tunnel): Transverse clearance: The horizontal clearance between the tunnel axis and the nearest pile foundation to the inspection platform is 3.7 meters (approximately 0.48 times the tunnel outer diameter D=7.7m); the minimum horizontal clearance to the pile foundation of the C3# pier of the Lianhua Ramp Bridge is 4.0 meters (0.52D); Vertical clearance: The vertical distance from the tunnel arch to the nearest pile tip is 11.0 meters (≈1.43D); the vertical distance from the tunnel arch to the pile tip of the C3# pier is 10.5 meters. S12. Define several types of factors that affect surface settlement and pile foundation deformation during the shield tunneling process, and obtain a set of settlement and deformation influencing factor types; the set of settlement and deformation influencing factor types includes ground loss, soil pressure, water and soil pressure at the excavation face, grouting pressure, jack thrust, tunnel geometric parameters (such as small radius curves, large slopes) and the interaction between the ground and the pile foundation (such as the pile foundation bearing additional axial and lateral forces), etc. By acquiring data on the types of strata, tunnel depth, and the types, depths, and distribution of building piles in the area where the shield tunnel passes under a building in advance, accurate basic geological and structural information can be provided for subsequent construction. This significantly improves the reliability of settlement and deformation prediction models and avoids misjudgments due to missing data. Simultaneously, by clearly defining key influencing factors such as stratum loss, construction parameters (e.g., soil pressure, grouting pressure, and jack thrust), tunnel geometric parameters (e.g., small-radius curves and steep slopes), and the interaction between the stratum and piles (e.g., additional axial and lateral forces borne by the piles), the main sources of construction disturbance can be comprehensively identified. This lays the theoretical foundation for developing targeted control measures, ensuring that under complex geological and structural conditions, the contribution of each factor to surface settlement and pile deformation can be effectively identified and quantified. This allows for optimization of construction parameter combinations, reducing stratum disturbance, lowering the risk of building settlement and pile displacement, and ensuring construction safety and the stability of existing structures. S2. Based on the settlement deformation influencing factor type in S1, obtain the current corresponding settlement deformation influencing factor data, and construct the current final shield tunneling under building model based on this. S2 includes the following steps: S21. Based on the set of settlement deformation influencing factors, obtain the initial data of various settlement deformation influencing factors corresponding to the current shield tunneling process under the building, and obtain the current initial settlement deformation influencing factor dataset. S22. Based on the current initial settlement deformation influencing factor dataset, current stratum type data, current tunnel depth data, and current building pile foundation dataset, and combined with the actual engineering situation, construct a three-dimensional numerical model corresponding to the current shield tunneling under the building process, and obtain the current final shield tunneling under the building model. Specifically, taking the shield tunneling under the inspection platform and the Lianhua ramp bridge of the Hengqin Line of the light rail extension in a certain region as an example, the current construction process of the final shield tunneling under the building model is as follows: S221. Establish a three-dimensional solid model including the tunnel (outer diameter 7.7m), inspection platform and lotus ramp bridge abutment, piers, pile foundation (modeled according to actual size) and surrounding soil; the soil range is at least 3 times the tunnel diameter (about 23m) outside and below the tunnel axis, and above to the ground surface, in order to fully simulate the far-field stratum constraints. S222. Assign corresponding constitutive models (such as the Mohr-Coulomb model) and parameters (unit weight, elastic modulus, Poisson's ratio, cohesion, internal friction angle, etc., see the exploration report for details) to different strata; assign linear elastic models (C35 concrete E=3.15×10) to concrete structures (segmentation, pile foundation, pile cap, pier) 4 MPa, ν=0.2, E is the elastic modulus, and ν represents Poisson's ratio); S223. Fixed constraints are applied to the bottom of the model, horizontal normal constraints are applied to the sides, and the top surface is a free boundary. S224. First, simulate the initial stratum state of stress equilibrium; then simulate the shield excavation process, using the "activation-passivation" function to simulate the shield machine's advance while simultaneously applying soil chamber pressure load; apply synchronous grouting pressure load at the shield tail position and simulate segment assembly; simulate stratum loss effects using the stratum "life and death" element technology; among which, the stratum "life and death" element technology is a commonly used technique in finite element numerical simulation to simulate construction processes such as tunnel excavation, foundation pit excavation, and shield tunneling. It dynamically simulates the removal of soil (excavation) or the installation (support) of structures by activating or passivating specific element groups in the model, thereby reproducing the impact of construction steps on the surrounding strata and structures; Finally, interface elements or nonlinear springs are used to simulate the interaction between the pile and the surrounding soil to reflect the stress and deformation of the pile foundation under the disturbance of shield tunneling construction. By integrating initial data on settlement and deformation influencing factors, data on traversed strata types, tunnel depth data, and building pile foundation datasets, and closely combining these with actual engineering practices, a three-dimensional numerical model is constructed. This model enables refined simulation of the shield tunneling process under buildings, significantly improving the prediction accuracy of strata response and structural deformation. The model comprehensively reflects the combined effects of key factors such as strata loss, construction parameters (e.g., soil pressure, grouting pressure, and jack thrust), tunnel geometric parameters (e.g., small-radius curves and steep slopes), and the interaction between the strata and pile foundations, providing a scientific basis for optimizing construction plans. By simulating settlement and deformation patterns under different working conditions, high-risk areas can be identified in advance, allowing for targeted adjustments to construction parameter combinations. This effectively controls the morphology of surface settlement troughs and the additional stress on pile foundations, reducing disturbance to existing structures and avoiding segment misalignment or pile foundation displacement due to parameter mismatch. Simultaneously, this model lays the foundation for subsequent dynamic monitoring and closed-loop control. Through real-time data feedback and model iteration, proactive control of the construction process is achieved, significantly reducing engineering risks and ensuring building safety and tunnel construction quality. S3. By collecting multi-dimensional historical data, establish a mapping model for surface settlement and pile foundation deformation; Please see Figure 3 S3 includes the following steps: S31. Based on the ground loss, grouting pressure, jack thrust, and tunnel geometric parameters in the aforementioned settlement deformation influencing factor type set, obtain the corresponding pile foundation data (including the type, depth, and distribution data of the building pile foundation), ground type data, grouting pressure data, left-right thrust ratio and up-down thrust ratio data of the jacks, tunnel parameter data (including burial depth data and geometric parameter data), and corresponding ground loss data, soil pressure, excavation face water and soil pressure, surface settlement data, and pile foundation deformation data during several historical shield tunneling processes under buildings. This yields historical grouting pressure dataset, historical left-right thrust ratio dataset of jacks, historical up-down thrust ratio dataset of jacks, historical tunnel geometric parameter dataset, historical ground loss dataset, historical soil pressure dataset, historical excavation face water and soil pressure dataset, historical surface settlement dataset, and historical pile foundation deformation dataset. For example, some historical data collected in S31 is shown in Table 2 below: Table 2. Example of historical data on tunnel sections passing under buildings.

[0022] S32. Based on the historical data collected in S31, construct a mapping model with the inputs of pile foundation data, stratum type data, grouting pressure data, jack left-right thrust ratio data, jack up-down thrust ratio data, tunnel parameter data, and the outputs of stratum loss data, soil pressure data, excavation face water and soil pressure data, surface settlement data, and pile foundation deformation data, to obtain the final pressure-settlement deformation mapping model. S32 includes the following steps: S321. Construct an initial pressure-settlement deformation mapping model and set a first training data ratio (e.g., 8:2 or 7:3, which can be adjusted adaptively according to the actual training situation); divide the historical grouting pressure dataset, historical jack left-right thrust ratio dataset, historical jack up-down thrust ratio dataset, historical tunnel geometric parameter dataset, historical stratum loss dataset, historical soil pressure dataset, historical excavation face water and soil pressure dataset, historical surface settlement dataset, and historical pile foundation deformation dataset according to the first training data ratio to obtain the first training dataset and the first test dataset. S322. Set a first training error threshold (10%~15%, which can be adjusted adaptively according to the actual training situation); input the first training dataset into the initial pressure-settlement deformation mapping model for training; during the training process, if the training error is less than the first training error threshold, stop training and obtain the trained pressure-settlement deformation mapping model; otherwise, continue training until the training error is less than the first training error threshold. S323. Set a first test accuracy threshold (90%~95%, which can be adjusted adaptively according to the actual test situation); input the first test dataset into the trained pressure-settlement deformation mapping model for testing; after the test is completed, obtain the first test accuracy data; if the first test accuracy data is greater than or equal to the first test accuracy threshold, use the trained pressure-settlement deformation mapping model as the final pressure-settlement deformation mapping model; otherwise, return to S322 to continue training the trained pressure-settlement deformation mapping model and repeat S323 until the first test accuracy data is greater than or equal to the first test accuracy threshold. The structure of the initial pressure-settlement deformation mapping model can be seen in Table 3 below: Table 3. Schematic diagram of the pressure-settlement deformation mapping model

[0023] Tunnel boring machine (TBM) construction involves a large number of geological parameters (soil properties, groundwater level), construction parameters (thrust, grouting, tunneling speed), and environmental parameters (spatial relationship with buildings). It has high feature dimensions and there may be implicit correlations between factors. Multilayer perceptrons can automatically learn and extract multi-level abstract representations of input features (such as soil physical and mechanical properties, relative tunnel depth, TBM tunneling posture, and existing building parameters). This enables the model to identify deep patterns that have a decisive influence on the final settlement or deformation (such as differential settlement of bridge piers and abutments, and horizontal displacement of pile foundations) from many interacting factors. By systematically collecting and analyzing the correlation data of various key parameters and deformation responses during the historical shield tunneling construction of buildings, a comprehensive and objective construction experience database can be established, providing reliable data support and decision-making basis for similar subsequent projects. The construction of this mapping model enables intelligent prediction from construction control parameters to settlement and deformation responses, significantly improving the predictive ability and risk control level of the construction process. Through model training driven by historical data, the nonlinear relationships and coupling effects between various influencing factors can be effectively identified, providing scientific guidance for the optimization and adjustment of construction parameters. At the same time, the model has good generalization ability and can be adaptively adjusted for shield tunneling construction under different geological conditions and engineering environments, laying a solid foundation for the precise and intelligent control of shield tunneling construction of buildings, thereby maximizing the safety and construction efficiency of existing buildings. In addition, the final pressure-settlement deformation mapping model is mutually verified and coordinated with the current final shield tunneling model, thereby further improving the accuracy of subsequent predictions of surface settlement and pile deformation. S4. Construct a mapping model using historical reinforcement data, then collect the current tunnel and pile foundation parameters and preset grouting parameters and input them into the mapping model in S4 to obtain the left and right and up and down reinforcement widths of the tunnel when the shield tunnel passes through the soft stratum and carry out reinforcement operations. Please see Figure 4 S4 includes the following steps: S41. Based on the stratum type described in S1, obtain the stratum type data, tunnel left and right and up and down reinforcement width, tunnel parameters (including tunnel depth, diameter, etc.), grouting parameters (including grouting pressure, grout viscosity, grouting volume, etc.), and pile foundation parameters (including pile type, length, and relative position to the tunnel, etc.) corresponding to several historical stratum type data before reinforcement, historical tunnel parameter set, historical grouting parameter set, historical pile foundation parameter set, historical left and right reinforcement width dataset, and historical up and down reinforcement width dataset, based on the stratum type data described in S1. S42. Based on the historical data collected in S41, construct a mapping model with the input of the stratum type data before reinforcement, the tunnel parameter set, the grouting parameters, and the pile foundation parameters, and the output of the left and right and up and down reinforcement width data of the tunnel, to obtain the final tunnel reinforcement width mapping model. S42 includes the following steps: S421. Construct an initial tunnel reinforcement width mapping model and set a second training data ratio (e.g., 8:2 or 7:3, which can be adjusted adaptively according to the actual training situation); divide the historical stratum type data before reinforcement, historical tunnel parameter set, historical grouting parameter set, historical pile foundation parameter set, historical left and right reinforcement width dataset, and historical upper and lower reinforcement width dataset according to the second training data ratio to obtain the second training dataset and the second test dataset. S422. Set a second training error threshold (10%~15%, which can be adjusted adaptively according to the actual training situation); input the second training dataset into the initial tunnel reinforcement width mapping model for training; during the training process, if the training error is less than the second training error threshold, stop training and obtain the trained tunnel reinforcement width mapping model; otherwise, continue training until the training error is less than the second training error threshold. S423. Set a second test accuracy threshold (90%~95%, which can be adjusted adaptively according to the actual test situation); input the second test dataset into the trained tunnel reinforcement width mapping model for testing; after the test is completed, obtain the second test accuracy data; if the second test accuracy data is greater than or equal to the second test accuracy threshold, use the trained tunnel reinforcement width mapping model as the final tunnel reinforcement width mapping model; otherwise, return to S422 to continue training the trained tunnel reinforcement width mapping model and repeat S423 until the second test accuracy data is greater than or equal to the second test accuracy threshold; The structure of the initial tunnel reinforcement width mapping model can be seen in Table 4 below: Table 4. Schematic diagram of the tunnel reinforcement width mapping model.

[0024] In a high-dimensional feature space, SVR constructs an optimal separating hyperplane as a regression function. The global optimal solution is determined by solving a convex quadratic programming problem, which avoids the defect of neural networks being prone to getting trapped in local optima. The model has good generalization ability, can handle small sample nonlinear problems, and is not sensitive to outliers. It is particularly suitable for handling reinforcement parameter design problems with limited sample size but high feature dimension in engineering practice. It can effectively predict the optimal values ​​of the left and right and top and bottom reinforcement widths around the tunnel. S43. Collect the tunnel parameter data and pile parameter data corresponding to the current shield tunneling process under the building, and obtain the preset grouting parameter data to obtain the current tunnel parameter dataset, the current pile parameter dataset and the current preset grouting parameter dataset. If the current stratum type data is a weak stratum, the current stratum type data, the current tunnel parameter dataset, the current pile parameter dataset, and the current preset grouting parameter dataset are input into the final tunnel reinforcement width mapping model for mapping to obtain the current left and right reinforcement width dataset and the current up and down reinforcement width dataset; otherwise, no grouting reinforcement operation is required. Then, based on the current left and right reinforcement width dataset, the current up and down reinforcement width dataset, and the current preset grouting parameter dataset, grouting reinforcement operations are performed on the left and right sides and up and down of the tunnel in the corresponding strata before the current shield tunnel passes under the building. After the operation is completed, the current stratum type data is updated to the current stratum type data after reinforcement. By constructing a tunnel reinforcement width mapping model driven by historical data and combining it with the actual parameters of the current project for intelligent prediction, the precise design and dynamic optimization of the grouting reinforcement range can be achieved, significantly improving the scientific and economic efficiency of ground pre-reinforcement construction. Through machine learning models, the complex nonlinear relationship between the reinforcement width and multiple dimensions such as ground type, tunnel depth, grouting parameters, and pile characteristics is automatically analyzed, avoiding the problems of insufficient or excessive reinforcement that may be caused by traditional empirical formulas or simple analogies. This effectively controls construction costs and ensures reinforcement results. Simultaneously, this method has good adaptability, automatically adjusting reinforcement parameters according to different geological conditions and engineering environments, providing personalized ground pre-reinforcement solutions for shield tunneling under buildings. This minimizes the disturbance of the surrounding soft strata during tunnel excavation, significantly reduces the risk of surface settlement and building deformation, and ensures the safety of existing structures and the stability of the construction process. S5. Set the standard range for several sets of parameters, including surface settlement and pile foundation deformation. Based on the reinforcement operation in S4, input the current multiple sets of parameters into the mapping model in S3 for mapping, and combine them with the prediction of the model in S2. If the mapped and predicted data are all within the corresponding standard range, no adjustment is needed; otherwise, repeatedly adjust the grouting pressure and jack thrust, remap and update the model parameters in S2 to re-predict until the standard requirements are met or S6 is executed. Please see Figure 5 S5 includes the following steps: S51. Based on the current engineering requirements for shield tunneling under buildings, obtain the standard range of current ground loss, soil pressure, excavation face water and soil pressure, surface settlement data, and pile foundation deformation data. S52. Input the current pile parameter dataset, the current tunnel parameter dataset, the current reinforced stratum type data, the current preset grouting pressure data, and the current preset left-right thrust ratio and up-down thrust ratio data of the jacks into the final pressure-settlement deformation mapping model for mapping to obtain the current initial stratum loss data, the current initial soil chamber pressure data, the current initial excavation face water and soil pressure data, the current initial surface settlement data, and the current initial pile foundation deformation data. Based on S51 and the predictions of the current final shield tunneling model, if the current initial ground loss data, current initial soil pressure data, current initial excavation face water and soil pressure data, current initial surface settlement data, and current initial pile foundation deformation data, and all the prediction data of the current final shield tunneling model are within the corresponding specification range, no adjustment is required; otherwise, execute S53. S53. Set a first repetition threshold (which can be adaptively set according to the project schedule requirements of the shield tunneling under the building); repeatedly adjust the current preset grouting pressure data, the current preset left-right thrust ratio of the jacks, and the current preset up-down thrust ratio data. In each repetition, the adjusted current preset grouting pressure data, the current preset left-right thrust ratio of the jacks, and the current preset up-down thrust ratio data are combined with the current pile parameter dataset, the current tunnel parameter dataset, and the current reinforced stratum type data and input again into the final pressure-settlement deformation mapping model for mapping and the parameters of the current final shield tunneling under the building model are reset. If the number of repetitions is less than or equal to the first repetition threshold, and all types of mapping data in the mapping results and all types of prediction data in the current final shield tunneling building model are within the corresponding specification range, the adjustment is complete; otherwise, proceed to S6. By constructing an intelligent parameter adjustment mechanism based on standard interval constraints, the key control indicators during shield tunneling under buildings can be automatically verified and dynamically optimized, significantly improving the safety and reliability of the construction process. By establishing a multi-dimensional data mapping relationship, the construction parameters and predicted deformation response are correlated and compared in real time, effectively avoiding parameter setting deviations that may be caused by traditional experience or single mapping models, ensuring that all key indicators are always within the safe range allowed by engineering specifications. S6. Repeat the hardening operation in S4 and repeat S5 until all types of data that have been remapped and re-predicted in S5 are within the corresponding specification range. Please see Figure 6 , Figure 7 S6 includes the following steps: S61. Repeat the grouting operation in S43 on the left, right and up and down of the tunnel in the corresponding stratum before the current shield tunnel passes under the building. After the operation is completed, update and obtain the current reinforced stratum type data again, and repeat S52 and S53 until the number of repetitions in S53 is less than or equal to the first repetition threshold, and all kinds of mapping data in the mapping results and all kinds of prediction data of the current final shield tunnel under the building model are within the corresponding specification range. By repeatedly performing grouting reinforcement operations and continuously updating the stratum state data, a closed-loop feedback control system is formed. This effectively solves the problem that simply adjusting the grouting pressure data and the left-right and up-down thrust ratios of the jacks is insufficient to meet the construction control requirements under complex geological conditions. Simultaneously, this scheme possesses excellent adaptive adjustment capabilities, dynamically adjusting the reinforcement strategy based on the prediction results after each iteration. This ensures that the final combination of construction parameters meets the specifications for key indicators such as surface settlement and pile foundation deformation, thereby maximizing the safety of existing structures and the stability of the construction process. This provides a reliable intelligent control method for shield tunnels passing through complex environments. By prioritizing the adjustment of grouting pressure data and the left-right and up-down thrust ratios of the jacks before repeating the grouting reinforcement operation, the operation progresses from easy to difficult, maximizing the efficiency of surface settlement and pile foundation deformation control.

[0025] Example 2 This embodiment discloses a joint control system for surface settlement and pile foundation deformation when a shield tunnel passes under a building. The system can implement the method of the above embodiment and includes a basic data acquisition module, a shield tunnel model construction module, a deformation mapping model construction module, a reinforcement data mapping module, a first adjustment module, and a second adjustment module. The basic data acquisition module is used to acquire data on the stratum type, tunnel depth, and pile foundation distribution of the building currently being tunneled under by the shield tunnel. The shield tunneling model building module is used to build the final shield tunneling model of the building. The deformation mapping model construction module is used to establish a mapping model for surface settlement and pile foundation deformation. The reinforcement data mapping module is used to map the left and right and up and down reinforcement widths of the tunnel when the shield tunnel passes under the soft strata and to perform reinforcement operations. The first adjustment module is used to repeatedly adjust the grouting pressure and the jack thrust. The second adjustment module is used to repeat the reinforcement operation and adjust the grouting pressure and jack thrust.

[0026] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0027] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present invention.

Claims

1. A method for jointly controlling surface settlement and pile foundation deformation when a shield tunnel passes under a building, characterized in that, Includes the following steps: S1. Set several types of settlement and deformation influencing factors and obtain the current data on the stratum type, tunnel depth and pile distribution of the building under which the shield tunnel passes; S2. Based on the settlement deformation influencing factor type in S1, obtain the current corresponding settlement deformation influencing factor data, and construct the current final shield tunneling under building model based on this. S3. Collect multi-dimensional historical data and establish a mapping model for surface settlement and pile foundation deformation. S4. Collect historical reinforcement data to construct a mapping model, then collect the current tunnel and pile foundation parameters and preset grouting parameters and input them into the mapping model in S4 to obtain the left and right and up and down reinforcement widths of the tunnel when the shield tunnel passes through the soft stratum and carry out reinforcement operations. S5. Set the standard range for several sets of parameters, including surface settlement and pile foundation deformation. Based on the reinforcement operation in S4, input the current multiple sets of parameters into the mapping model in S3 for mapping, and combine them with the prediction of the model in S2. If the mapped and predicted data are all within the corresponding standard range, no adjustment is needed; otherwise, repeatedly adjust the grouting pressure and jack thrust, remap and update the model parameters in S2 to re-predict until the standard requirements are met or S6 is executed. S6. Repeat the hardening operation in S4 and repeat S5 until all types of data remapped and re-predicted in S5 are within the corresponding specification range.

2. The method for jointly controlling surface settlement and pile foundation deformation when a shield tunnel passes under a building, as described in claim 1, is characterized in that: The types of factors affecting settlement and deformation described in S1 include ground loss, soil pressure, water and soil pressure at the excavation face, grouting pressure, jack thrust, tunnel geometric parameters, and the interaction between the ground and the pile foundation.

3. The method for jointly controlling surface settlement and pile foundation deformation when a shield tunnel passes under a building, as described in claim 2, is characterized in that: The current final shield tunneling model described in S2 is the three-dimensional numerical model corresponding to the current shield tunneling process, thus obtaining the current final shield tunneling model.

4. The method for jointly controlling surface settlement and pile foundation deformation when a shield tunnel passes under a building, as described in claim 1, is characterized in that... The collection of multi-dimensional historical data in S3 includes the following steps: S31. Obtain data on pile foundations, stratum types, grouting pressure, jack thrust ratios (left and right and up and down), tunnel parameters, and corresponding stratum loss, soil pressure, excavation face water and soil pressure, surface settlement, and pile deformation during several historical shield tunneling operations.

5. The method for joint control of surface settlement and pile foundation deformation when a shield tunnel passes under a building, as described in claim 4, is characterized in that: The inputs to the mapping model described in S3 are pile foundation data, stratum type data, grouting pressure data, jack left-right thrust ratio data, jack up-down thrust ratio data, and tunnel parameter data. The outputs are stratum loss data, soil pressure data, excavation face water and soil pressure data, surface settlement data, and pile foundation deformation data.

6. The method for joint control of surface settlement and pile foundation deformation when a shield tunnel passes under a building, as described in claim 2, is characterized in that... The mapping model described in S4 takes as input data the stratum type before reinforcement, tunnel parameter set, grouting parameters, and pile foundation parameters, and outputs as data on the left, right, and top and bottom reinforcement widths of the tunnel.

7. The method for joint control of surface settlement and pile foundation deformation when a shield tunnel passes under a building, as described in claim 6, is characterized in that... S4 includes the following steps: S41. Collect the tunnel parameter data and pile parameter data corresponding to the current shield tunneling process under the building, and obtain the pre-set grouting parameter data. S42. If the current stratum type data is soft stratum, input the data collected in S41 and the current stratum type data into the mapping model in S4 for mapping, and based on the mapping results, perform grouting reinforcement operations on the left, right and up and down of the tunnel in the corresponding stratum before the current shield tunnel passes under the building to obtain the current reinforced stratum type data; otherwise, no grouting reinforcement operation is required.

8. The method for joint control of surface settlement and pile foundation deformation when a shield tunnel passes under a building, as described in claim 7, is characterized in that... S5 includes the following steps: S51. Input the current pile parameter data, current tunnel parameter data, current reinforced stratum type data, current preset grouting pressure data, and current preset left-right thrust ratio and up-down thrust ratio data of the jack into the mapping model in S3 for mapping. S52. If all data in the mapping results in S51 and all prediction data of the current final shield tunneling building model are within the corresponding specification range, no adjustment is needed; otherwise, proceed with S53. S53. Set the first repetition threshold; repeatedly adjust the current preset grouting pressure data, the current preset left-right thrust ratio of the jack, and the current preset up-down thrust ratio data. In each repetition, the adjusted current preset grouting pressure data, the current preset left-right thrust ratio of the jack, and the current preset up-down thrust ratio data are combined with the current pile parameter data, the current tunnel parameter data, and the current reinforced stratum type data and input back into the mapping model in S3 for mapping and reset the parameters of the current final shield tunneling building model. If the number of repetitions is less than or equal to the first repetition threshold, and all types of mapping data in the mapping results and all types of predicted data in the current final shield tunneling building model are within the corresponding specification range, the adjustment is complete; otherwise, proceed to step S6.

9. The method for joint control of surface settlement and pile foundation deformation when a shield tunnel passes under a building, as described in claim 7, is characterized in that... S6 includes the following steps: S61. Repeat S42 to perform grouting on the left, right and up and down of the tunnel in the corresponding stratum before the current shield tunnel passes under the building. After the operation is completed, update and obtain the current reinforced stratum type data again, and repeat S52 and S53 until the number of repetitions in S53 is less than or equal to the first repetition threshold, and all kinds of mapping data in the mapping results and all kinds of prediction data of the current final shield tunnel under the building model are within the corresponding specification range.

10. A system for jointly controlling surface settlement and pile foundation deformation during shield tunneling under a building as described in any one of claims 1-9, characterized in that: It includes a basic data acquisition module, a shield tunneling model construction module, a deformation mapping model construction module, a reinforcement data mapping module, a first adjustment module, and a second adjustment module; The basic data acquisition module is used to acquire data on the stratum type, tunnel depth, and pile foundation distribution of the building currently being tunneled under by the shield tunnel. The shield tunneling model building module is used to build the final shield tunneling model of the building. The deformation mapping model construction module is used to establish a mapping model for surface settlement and pile foundation deformation. The reinforcement data mapping module is used to map the left and right and up and down reinforcement widths of the tunnel when the shield tunnel passes under the soft strata and to perform reinforcement operations. The first adjustment module is used to repeatedly adjust the grouting pressure and the jack thrust. The second adjustment module is used to repeat the reinforcement operation and adjust the grouting pressure and jack thrust.

Images