Method and device for controlling ground surface deformation in shield construction based on digital twinning

Abstract

This invention discloses a method and device for controlling surface deformation during shield tunneling construction based on digital twins, comprising: step S1, constructing an initial digital model of shield tunneling construction based on on-site shield tunneling construction data; step S2, collecting on-site shield tunneling construction parameters and ground response data caused by on-site shield tunneling construction in real time, and updating the digital model of shield tunneling construction constructed in step S1, thereby obtaining the mapping relationship between the digital model of shield tunneling construction and the shield tunneling construction parameters; step S3, based on the mapping relationship between the digital model of shield tunneling construction and the shield tunneling construction parameters, using a reinforcement learning algorithm to take the digital model of shield tunneling construction as the interaction environment for reinforcement learning, the set of construction parameters as the action space, and the reward function as the surface deformation, so as to minimize the surface deformation and determine the optimal sequence of construction parameter actions.

Description

Technical Field

[0001] This invention relates to the field of civil engineering monitoring technology, and in particular to a method and device for controlling surface deformation during shield tunneling construction based on digital twins. Background Technology

[0002] my country's urban rail transit is in a phase of rapid development. Tunnel boring machine (TBM) technology is widely used in the construction of urban underground rail transit. TBM construction inevitably disturbs the surrounding soil, causing surface deformation. Excessive surface deformation can lead to uneven settlement of existing buildings, wall cracking, and other problems. In the soft soil areas of eastern coastal my country, soil conditions are poor, and the urban environment is highly sensitive to construction projects. Existing technologies for controlling surface deformation caused by TBM construction are insufficient to meet the requirements for controlling micro-deformation of the surface.

[0003] Currently, the main technologies for controlling surface deformation caused by tunnel boring machine (TBM) construction include on-site monitoring, empirical methods, analytical methods, indoor model tests, and numerical methods. On-site monitoring is a post-construction control method, and it is difficult to predict and assess surface deformation caused by TBM construction using only measured data. Empirical methods are not good at considering the influence of complex engineering geological conditions, construction technology, and construction parameters on surface deformation. Analytical methods are based on linear elastic theory, which simplifies the mechanical properties of soil and rock materials and the calculation model to varying degrees, making it difficult to simulate the actual TBM construction process. Indoor model tests are difficult to construct, and their similarity ratio is not easy to meet the specified requirements. The calculation accuracy of numerical methods depends on the degree of agreement between the digital model and the actual project, and it is not easy to optimize and adjust the TBM construction parameters. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and device for controlling surface deformation during shield tunneling construction based on digital twins.

[0005] According to a first aspect of the present invention, a method for controlling surface deformation during shield tunneling construction based on digital twins is provided, the method comprising:

[0006] Step S1: Based on the on-site shield tunneling construction data, construct an initial digital model of the shield tunneling construction.

[0007] Step S2: Real-time acquisition of on-site shield tunneling construction parameters and ground response data caused by on-site shield tunneling construction, updating the shield tunneling digital model constructed in step S1, thereby obtaining the mapping relationship between the shield tunneling digital model and the shield tunneling construction parameters.

[0008] Step S3: Based on the mapping relationship between the digital model of shield tunneling construction and the shield tunneling construction parameters, the digital model of shield tunneling construction is used as the interaction environment for reinforcement learning, the set of construction parameters is used as the action space, and the reward function is the ground deformation. The optimal sequence of construction parameter actions is determined by minimizing the ground deformation.

[0009] Furthermore, the digital model for tunnel boring machine construction includes:

[0010] The shield tunneling construction parameter storage module is used to record the construction parameters of the shield tunneling project in real time.

[0011] The ground response data storage module is used to store the ground response data collected during the shield tunneling construction process.

[0012] The digital simulation module is used to extract basic attribute information reflecting the real object, including geometric dimensions, material properties, and mechanical properties, from the design data, geological data, shield construction parameters, and surrounding environment of the on-site shield construction project, and convert them into corresponding models.

[0013] Furthermore, the construction parameters for on-site tunnel boring machine (TBM) construction include tunneling speed, cutterhead torque, support pressure, and grouting pressure.

[0014] Furthermore, the ground response data during the tunnel boring machine (TBM) construction process includes pore water pressure, surface vertical displacement, and deep horizontal displacement.

[0015] Furthermore, the ground response data during the tunnel boring machine (TBM) construction process is measured using a pore water pressure gauge, a fiber optic grating static leveling instrument, and a deep horizontal displacement monitoring instrument.

[0016] Furthermore, the digital simulation module includes:

[0017] A geometric model is established based on the proposed tunnel's burial depth, design dimensions, and soil layer distribution.

[0018] Based on soil parameters, lining structure, bolted connections, splicing methods, and longitudinal linearity, and combined with lining segment model tests, a mechanism model that can reflect the working performance of the lining segments is selected, and a property model is established.

[0019] A working condition simulation model is established based on the support of the shield excavation face, soil excavation, lining installation and shield tail grouting.

[0020] An environmental simulation model was established based on the actual conditions of the proposed tunnel. The actual conditions of the proposed tunnel include adjacent foundation pit excavation, passage through historical protected buildings, and / or passage through existing tunnels.

[0021] The geometric model, attribute model, working condition simulation model, and environmental simulation model are integrated to form the digital simulation module in the initial digital model of shield tunneling construction.

[0022] Further, step S2 includes the following sub-steps:

[0023] Step S201: Minimize surface subsidence as the objective function. The expression is as follows:

[0024]

[0025] In the formula, n represents the total number of measurement points, and i represents the i-th measurement point. This represents the predicted value of the formation response data at the i-th measuring point. This represents the true value of the formation response data at the i-th measuring point;

[0026] Step S202: Real-time acquisition of shield tunneling construction parameters, adjacent project construction conditions, and actual values ​​of surface settlement caused by shield tunneling construction, and inputting them into the initial shield tunneling digital model constructed in step S1. The shield tunneling digital model outputs predicted values ​​of surface settlement.

[0027] Step S203: Repeat step S202 above, use a genetic algorithm to compare the predicted value of surface settlement with the actual value of surface settlement, and obtain the mapping relationship between the digital model of shield tunneling construction and the shield tunneling construction parameters according to the objective function set in step S201.

[0028] Further, step S3 includes:

[0029] Under the constraint of a given surface settlement target, based on the mapping relationship between the digital model of shield tunneling construction and shield tunneling parameters, multiple sets of construction parameter combination vectors are randomly generated. These construction parameter combination vectors are then input into a neural network to obtain the surface settlement. A genetic algorithm is used to adjust the input construction parameter combination vectors for optimization, and the construction parameter combination vector corresponding to the minimum surface settlement is taken as the optimal construction parameter action sequence.

[0030] According to a second aspect of the present invention, a control device for surface deformation during shield tunneling based on digital twins is provided, comprising one or more processors for implementing the above-described control method for surface deformation during shield tunneling based on digital twins.

[0031] According to a third aspect of the present invention, a computer-readable storage medium is provided having a program stored thereon, characterized in that, when executed by a processor, the program is used to implement the above-described method for controlling surface deformation during shield tunneling based on digital twins.

[0032] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0033] This invention is based on the concept of digital twins. By creating a digital model of tunnel boring machine (TBM) construction on an information platform, a mapping relationship is established between the model and the actual TBM construction project in virtual space, thereby achieving synchronization between the virtual and real worlds. The actual TBM construction project is the "real" part of this synchronization, while the digital model of the TBM construction is the "virtual" part.

[0034] This invention utilizes reinforcement learning to minimize ground deformation caused by shield tunneling. It analyzes the relationship between shield tunneling parameters and ground response data to continuously optimize and adjust the construction parameters. The construction parameters obtained through reinforcement learning are input into the digital model of shield tunneling to predict the amount of ground deformation, and the most reasonable shield tunneling parameters are determined through iteration.

[0035] This invention features real-time, dynamic, multi-directional transmission, high fidelity, and closed-loop characteristics. On the one hand, the state parameters of the on-site shield tunneling project can be effectively transmitted to the digital model of shield tunneling, ensuring the synchronization between the digital model and the actual state. On the other hand, the ground response data and shield tunneling parameters obtained from the analysis of the digital model of shield tunneling can be fed back to the on-site shield tunneling project, thereby adjusting the on-site shield tunneling project.

[0036] This invention can provide real-time status, development trend and adjustment scheme of surface deformation caused by shield tunneling, effectively reduce the disturbance of shield tunneling to the surrounding environment, and thus protect existing structures, providing new possibilities for the digitalization and automation of shield tunneling project monitoring. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. 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 effort.

[0038] Figure 1 This is a schematic diagram of the digital simulation module in the digital model of shield tunneling construction provided in an embodiment of the present invention;

[0039] Figure 2 A schematic diagram of a digital model of shield tunneling provided in an embodiment of the present invention;

[0040] Figure 3 A schematic diagram illustrating the process of creating a mapping relationship between a digital model of shield tunneling construction and the actual shield tunneling construction project in an embodiment of the present invention;

[0041] Figure 4 This is a schematic diagram of the process for obtaining optimal construction parameters provided in an embodiment of the present invention;

[0042] Figure 5 A schematic diagram of a control device for surface deformation during shield tunneling based on digital twins, provided in an embodiment of the present invention. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] It should be noted that, unless otherwise specified, the features in the following embodiments and implementation methods can be combined with each other.

[0045] This invention provides a method for controlling surface deformation during shield tunneling based on digital twins. The method specifically includes the following steps:

[0046] Step S1: Based on the on-site shield tunneling construction data, construct an initial digital model of the shield tunneling construction.

[0047] The digital model for shield tunneling construction consists of three parts: a shield tunneling construction parameter storage module, a ground response data storage module, and a digital simulation module.

[0048] The shield tunneling parameter storage module is used to record various parameters of the shield tunneling project in real time, such as tunneling speed, cutterhead torque, support pressure, and grouting pressure.

[0049] The ground response data storage module is used to store ground response data collected during the shield tunneling process, such as pore water pressure, surface vertical displacement, and deep horizontal displacement. The ground response data can be detected by a monitoring system consisting of pore water pressure gauges, fiber optic static leveling points, and deep horizontal displacement monitoring equipment.

[0050] The digital simulation module is used to extract relevant information reflecting the basic attributes of the real object, such as geometric dimensions, material properties, and mechanical properties, from the design data, geological data, shield construction parameters, and surrounding environment of the on-site shield tunneling project, and then convert them into corresponding models.

[0051] For example, such as Figure 1As shown, a geometric model is established based on the proposed tunnel's burial depth, design dimensions, and soil layer distribution. A mechanistic model reflecting the lining segment's performance is selected based on soil parameters, lining structure, bolt connections, splicing methods, and longitudinal linearity, combined with lining segment model tests, thus establishing an attribute model. The operational simulation mainly includes shield face support, soil excavation, lining installation, and shield tail grouting. Environmental simulation is conducted based on the actual conditions of the proposed tunnel, such as adjacent foundation pit excavation, protection of surrounding historical buildings, and dynamic monitoring of pipelines. Finally, all the above models are integrated to form the digital simulation module in the initial digital model of shield tunneling construction.

[0052] Step S2: Real-time acquisition of on-site shield tunneling construction parameters and ground response data caused by on-site shield tunneling construction, updating the shield tunneling digital model constructed in step S1, thereby obtaining the mapping relationship between the shield tunneling digital model and the shield tunneling construction parameters.

[0053] Specifically, such as Figure 2 As shown, step S2 specifically includes the following sub-steps:

[0054] Step S201: Minimize surface subsidence as the objective function. The expression is as follows:

[0055]

[0056] In the formula, n represents the total number of measurement points, and i represents the i-th measurement point. This represents the predicted surface subsidence value at the i-th measuring point. This represents the actual value of the surface subsidence at the i-th measuring point.

[0057] It should be noted that in this example, the objective function The mean squared error loss function is selected, and a higher (squared) penalty is imposed on sample points where the actual value of surface subsidence deviates significantly from the predicted value.

[0058] Step S202: Real-time collection of shield tunneling construction parameters, adjacent project construction status, and ground response data (i.e., actual surface settlement values) caused by shield tunneling construction, and input of these data into the initial shield tunneling digital model constructed in step S1. The shield tunneling digital model outputs the predicted values ​​of the ground response data (i.e., predicted surface settlement values).

[0059] Among them, such as Figure 3 As shown, in this example, simulating shield tunnel construction and outputting predicted surface settlement values ​​through a digital model of shield construction includes the following steps:

[0060] Step S20201: Construct a structural model for shield tunnel construction, considering boundary effects;

[0061] Step S20202: The ground settlement caused by the shield tunneling method is simulated using the equivalent layer method;

[0062] Step S20203: The Mohr-Coulomb constitutive model is used to simulate the soil around the tunnel, the empty model is used to simulate the soil excavated during shield tunneling, and the linear elastic model is used to simulate the tunnel segments, the shield machine steel shell and the equivalent layer.

[0063] Step S20204: Apply support force to simulate the combined force of slurry chamber pressure, total thrust, etc. on the support surface, and apply grouting pressure to simulate the pressure of synchronous grouting at the shield tail.

[0064] Step S20205: While the tunnel boring machine is excavating, the change in synchronous grouting effect is simulated by changing the parameters of the equivalent layer. After maintaining the initial grout material parameters of one excavation cycle, each grout section is changed to the later grout parameters (hardening) and kept unchanged.

[0065] Step S20206: During the tunnel boring machine (TBM) advancement process, after each excavation cycle, the material parameters at the corresponding locations are changed. For example, corresponding shield parameters are set around the excavated soil in front, and the shield tail unit is killed. At the same time, the loads and forces at the corresponding locations are also changed to the corresponding positions as the excavation moves forward, to simulate the process of the TBM advancing forward.

[0066] Step S203: Based on the objective function set in step S201, repeat step S202 above. Using a genetic algorithm, compare the predicted value of the stratum response data with the actual value of the stratum response data so that the shield tunneling digital model (virtual part) can accurately reflect the on-site shield tunneling project (real part), thereby obtaining the mapping relationship between the shield tunneling digital model and the shield tunneling parameters.

[0067] Updating the digital model of shield tunneling construction using a genetic algorithm includes: determining the soil mechanical parameters based on the principle of minimizing the MSE between the measured ground response data and the digital model ground response data; stopping the search when the MSE is less than 1e-4 or when the population size reaches 100; performing 5 iterations.

[0068] Step S3: After the digital model of the tunnel boring machine (TBM) construction is updated, based on the mapping relationship between the digital model and the TBM construction parameters, reinforcement learning algorithms (A2C, DQN, and PPO) are used. The digital model serves as the interaction environment for reinforcement learning, the set of construction parameters serves as the action space, and the reward function is -abs (surface deformation). The optimal sequence of construction parameter actions is determined to minimize surface deformation. The reinforcement learning stops training when the absolute value of the maximum surface deformation is less than 1e-4m, or when the number of training environment steps reaches 1e5.

[0069] Specifically, such as Figure 4As shown, under the constraint of a given surface settlement target, the optimal combination of construction parameters needs to be determined. A reinforcement learning algorithm is used to obtain the intrinsic relationship between each construction parameter and surface settlement, establishing the relationship between shield tunneling parameters and surface settlement above the tunnel axis. Then, multiple sets of construction parameter combination vectors are randomly generated, and the corresponding output quantity—surface settlement—is calculated using a neural network. The fitness value of the output quantity is obtained from the objective function. Based on the fitness value, a genetic algorithm is used to adjust the input construction parameter combination vector. After optimization by the genetic algorithm, the most ideal surface settlement can be obtained, and the corresponding input vector is the optimal combination of construction parameters.

[0070] Corresponding to the aforementioned embodiments of the method for controlling surface deformation during shield tunneling based on digital twins, the present invention also provides embodiments of a device for controlling surface deformation during shield tunneling based on digital twins.

[0071] See Figure 5 The present invention provides a control device for surface deformation during shield tunneling based on digital twins, comprising one or more processors for implementing the control method for surface deformation during shield tunneling based on digital twins in the above embodiments.

[0072] The embodiment of the control device for surface deformation during shield tunneling based on digital twins of this invention can be applied to any device with data processing capabilities, such as a computer. The device embodiment can be implemented through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor of any data processing device loading the corresponding computer program instructions from non-volatile memory into memory for execution. From a hardware perspective, such as... Figure 5 The diagram shown is a hardware structure diagram of any data processing-capable device, including the control device for surface deformation during shield tunneling based on digital twins, according to the present invention. (Except for...) Figure 5 In addition to the processor, memory, network interface, and non-volatile memory shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0073] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0074] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the present invention according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0075] This invention also provides a computer-readable storage medium storing a program thereon, which, when executed by a processor, implements the method for controlling surface deformation during shield tunneling based on digital twins as described in the above embodiments.

[0076] The computer-readable storage medium can be an internal storage unit of any data processing device described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be any data processing device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data processing device, and can also be used to temporarily store data that has been output or will be output.

[0077] The above embodiments are only used to illustrate the design concept and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly. The protection scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes or modifications made based on the principles and design ideas disclosed in the present invention are within the protection scope of the present invention.

Claims

1. A method for controlling surface deformation during shield tunneling construction based on digital twins, characterized in that, The method includes: Step S1: Based on the on-site shield tunneling construction data, construct an initial digital model of the shield tunneling construction. Step S2: Real-time acquisition of on-site shield tunneling construction parameters and ground response data caused by on-site shield tunneling construction, updating the shield tunneling digital model constructed in step S1, thereby obtaining the mapping relationship between the shield tunneling digital model and the shield tunneling construction parameters. Step S3: Based on the mapping relationship between the digital model of shield tunneling construction and the shield tunneling construction parameters, the digital model of shield tunneling construction is used as the interaction environment for reinforcement learning, the set of construction parameters is used as the action space, and the reward function is the ground deformation. The optimal action sequence of construction parameters is determined by minimizing the ground deformation. Step S2 includes the following sub-steps: Step S201: Minimize surface subsidence as the objective function. The expression is as follows: ； In the formula, n represents the total number of measurement points, and i represents the i-th measurement point. This represents the predicted value of the formation response data at the i-th measuring point. This represents the true value of the formation response data at the i-th measuring point; Step S202: Real-time acquisition of shield tunneling construction parameters, adjacent project construction conditions, and actual values ​​of surface settlement caused by shield tunneling construction, and inputting them into the initial shield tunneling digital model constructed in step S1. The shield tunneling digital model outputs predicted values ​​of surface settlement. Step S203: Repeat step S202 above, use a genetic algorithm to compare the predicted value of surface settlement with the actual value of surface settlement, and obtain the mapping relationship between the digital model of shield tunneling construction and the shield tunneling construction parameters according to the objective function set in step S201. Step S3 includes: Under the constraint of a given surface settlement target, based on the mapping relationship between the digital model of shield tunneling construction and shield tunneling parameters, multiple sets of construction parameter combination vectors are randomly generated. These construction parameter combination vectors are then input into a neural network to obtain the surface settlement. A genetic algorithm is used to adjust the input construction parameter combination vectors for optimization, and the construction parameter combination vector corresponding to the minimum surface settlement is taken as the optimal construction parameter action sequence.

2. The method for controlling surface deformation during shield tunneling based on digital twins according to claim 1, characterized in that, The digital model for tunnel boring machine construction includes: The shield tunneling construction parameter storage module is used to record the construction parameters of the shield tunneling project in real time. The ground response data storage module is used to store the ground response data collected during the shield tunneling construction process. The digital simulation module is used to extract basic attribute information reflecting the real object, including geometric dimensions, material properties, and mechanical properties, from the design data, geological data, shield construction parameters, and surrounding environment of the on-site shield tunneling project, and convert them into corresponding models.

3. The method for controlling surface deformation during shield tunneling based on digital twins according to claim 2, characterized in that, The construction parameters for on-site tunnel boring machine (TBM) construction include tunneling speed, cutterhead torque, support pressure, and grouting pressure.

4. The method for controlling surface deformation during shield tunneling based on digital twins according to claim 2, characterized in that, The ground response data during shield tunneling includes pore water pressure, surface vertical displacement, and deep horizontal displacement.

5. The method for controlling surface deformation during shield tunneling based on digital twins according to claim 2, characterized in that, The ground response data during the tunnel boring machine (TBM) construction process is measured using a pore water pressure gauge, a fiber optic grating static leveling instrument, and a deep horizontal displacement monitoring instrument.

6. The method for controlling surface deformation during shield tunneling based on digital twins according to claim 2, characterized in that, The digital simulation module includes: A geometric model is established based on the proposed tunnel's burial depth, design dimensions, and soil layer distribution. Based on soil parameters, lining structure, bolted connections, splicing methods, and longitudinal linearity, and combined with lining segment model tests, a mechanism model that can reflect the working performance of the lining segments is selected, and a property model is established. A working condition simulation model is established based on the support of the shield excavation face, soil excavation, lining installation and shield tail grouting. An environmental simulation model was established based on the actual conditions of the proposed tunnel. The actual conditions of the proposed tunnel are: adjacent to the foundation pit excavation, passing through historical buildings and / or passing through existing tunnels. The geometric model, attribute model, working condition simulation model, and environmental simulation model are integrated to form the digital simulation module in the initial digital model of shield tunneling construction.

7. A control device for surface deformation during shield tunneling construction based on digital twins, characterized in that, It includes one or more processors for implementing the method for controlling surface deformation during shield tunneling based on digital twins, as described in any one of claims 1-6.

8. A computer-readable storage medium having a program stored thereon, characterized in that, When executed by the processor, the program is used to implement the method for controlling surface deformation during shield tunneling based on digital twins, as described in any one of claims 1-6.

Images