Method and system for predicting horizontal bearing capacity of rock-socketed single pile for digital mechanical twinning

Abstract

The invention discloses a method and system for predicting the horizontal bearing capacity of a rock-socketed single pile for digital mechanical twinning, and relates to the technical field of single pile bearing capacity prediction.The method comprises the steps that a numerical sample library is constructed through FDEM numerical simulation, mechanical state variables are extracted, and a training set is constructed based on pile top displacement, pile top load and mechanical state variables of each loading step; constructing an agent model taking pile body design parameters, rock mass design parameters and target pile top displacement as inputs and taking pile top loads and mechanical state variables as outputs, training the agent model by adopting the training set, and enabling a predicted value output by the agent model to approach a FDEM numerical simulation value by optimizing a loss function; and obtaining a horizontal load-displacement response curve and a mechanical state variable evolution process by adopting the trained proxy model according to a to-be-predicted pile foundation design parameter. The prediction precision and the calculation efficiency are guaranteed, and good physical consistency and extrapolation capability are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of single pile bearing capacity prediction, in particular to a rock-embedded single pile horizontal bearing capacity prediction method and system for digital mechanics twinning. BACKGROUND

[0002] The statements in this section merely provide background information related to the present application and do not necessarily constitute prior art.

[0003] Rock-embedded single piles are widely used as foundations in major projects such as bridges, offshore wind power, high-rise buildings, etc. The horizontal bearing capacity of rock-embedded single piles directly determines the lateral stability and safety and reliability of the superstructure. Due to the complex interaction mechanism between the pile and the surrounding rock mass, involving nonlinear deformation of rock mass, crack propagation, pile-rock interface slip, and pile bending moment distribution, the response prediction of rock-embedded single piles under horizontal load is extremely challenging. Therefore, accurately predicting the horizontal bearing capacity and load-displacement response has become a key link in engineering design and safety assessment.

[0004] Currently, the prediction methods for the horizontal bearing capacity of rock-embedded single piles mainly include traditional theoretical analysis, numerical simulation, and data-driven artificial intelligence methods.

[0005] Traditional theoretical methods are mostly based on the Winkler foundation model or the p-y curve method, which are computationally efficient but cannot accurately reflect the nonlinear damage and progressive failure process of rock mass, especially in complex geological conditions, with limited prediction accuracy.

[0006] Numerical simulation methods, such as finite element method (FEM) and finite element-discrete element coupling method (FDEM), can simulate the mechanical behavior of pile-rock systems in detail, but the calculation cost is high and the modeling is complex, making it difficult to meet the needs of rapid and multi-condition iteration in engineering design.

[0007] In recent years, with the development of artificial intelligence technology, AI models purely driven by data (such as neural networks, support vector machines, etc.) have been introduced into bearing capacity prediction, which have strong nonlinear fitting ability, but the prediction results often lack clear physical mechanism support, have "black box" problems, and lack physical consistency in extrapolation prediction, making it difficult to ensure reliability and generalization ability in unknown conditions. SUMMARY

[0008] To solve the above problems, the application provides a rock-embedded single pile horizontal bearing capacity prediction method and system for digital mechanics twinning, which combines mesoscopic physical mechanism and deep learning technology, extracts key mechanical state variables from high-fidelity FDEM simulation, and constructs a proxy model architecture combining physical kernel and residual learning, embeds physical laws into artificial intelligence models in a hard constraint manner, ensures prediction accuracy and computing efficiency, and has good physical consistency and extrapolation ability, solving the deficiencies of existing methods in terms of accuracy, efficiency and physical credibility.

[0009] To achieve the above-mentioned purpose, the application adopts the following technical solutions: In a first aspect, the application provides a rock-embedded single pile horizontal bearing capacity prediction method for digital mechanics twinning, comprising: Through FDEM numerical simulation, a numerical sample library of rock-embedded single pile horizontal loading under multiple working conditions is constructed, and mechanical state variables representing the physical state of the pile-rock system are extracted from the FDEM numerical simulation results, thereby constructing a training set based on the pile top displacement, pile top load and mechanical state variables of each loading step; An agent model is constructed with the pile design parameters, rock design parameters and target pile top displacement as input, and the pile top load and mechanical state variables as output, and the agent model is trained using the training set, and the predicted value output by the agent model is approximated to the FDEM numerical simulation value by optimizing the loss function; According to the pile foundation design parameters to be predicted, the trained agent model is used to obtain the horizontal load-displacement response curve and the mechanical state variable evolution process.

[0010] As an optional implementation, the mechanical state variables include damage factor, plastic strain and pile body bending moment; after aligning the pile top displacement, pile top load and three mechanical state vectors of each loading step, a structured state evolution sequence is constructed for each FDEM numerical simulation.

[0011] As an optional implementation, the process of extracting mechanical state variables includes: Along the embedded depth direction of the pile, the rock around the pile is divided into continuous control intervals; For each loading step, all rock elements of the FDEM are traversed, and the control interval to which the rock element center coordinates belong is determined; The volume-weighted average value of the field variable of all rock elements in each control interval is calculated, the field variable includes damage factor and plastic strain, and the pile body bending moment value at the depth corresponding to each control interval is extracted.

[0012] As an optional implementation, the agent model includes a physical kernel layer and a residual learning branch; The physical core layer takes the pile body design parameter and the rock mass design parameter as input, and outputs the physical prediction value of the pile top load and the physical prediction value of the bending moment of the pile body along the pile body; The residual learning branch takes the pile body design parameter, the rock mass design parameter, the target pile top displacement, and the soil reaction force calculated by the physical core layer as input, and outputs the pile top load residual, the pile body bending moment residual, and the damage factor prediction value and the plastic strain prediction value; the pile top load residual is the difference between the pile top load simulation value and the pile top load physical prediction value, and the pile body bending moment residual is the difference between the pile body bending moment simulation value and the pile body bending moment physical prediction value.

[0013] As an optional implementation, the loss function Loss is: ; Wherein, 、 、 and are the mean square error losses of the pile top load prediction value , the pile body bending moment prediction value , the damage factor prediction value and the plastic strain prediction value ; 、 、 、 and are weight coefficients; 、 、 and are the true values of the pile top load, the pile body bending moment, the damage factor and the plastic strain, respectively; is a physical constraint penalty term.

[0014] As an optional implementation, the physical constraint penalty term includes: The soil reaction force is calculated based on the pile body bending moment prediction value, and satisfies the static equilibrium equation: ; The damage factor prediction value monotonically increases with the loading displacement; The damage factor prediction value is negatively correlated with the pile body bending moment prediction value or the soil reaction force .

[0015] In a second aspect, the present application provides a rock-embedded single pile horizontal bearing capacity prediction system for digital mechanics twin, comprising: The numerical simulation module is configured to construct a numerical sample library of rock-embedded single pile horizontal loading containing multiple working conditions through FDEM numerical simulation, and extract mechanical state variables representing the physical state of the pile-rock system from the FDEM numerical simulation results, thereby constructing a training set based on the pile top displacement, pile top load and mechanical state variables of each loading step; The model construction and training module is configured to construct a proxy model with the pile body design parameters, rock mass design parameters and target pile top displacement as inputs, and the pile top load and mechanical state variables as outputs, and train the proxy model using the training set, and make the predicted values output by the proxy model approach the FDEM numerical simulation values by optimizing the loss function. The prediction module is configured to obtain the horizontal load-displacement response curve and the mechanical state variable evolution process by using the trained proxy model according to the pile foundation design parameters to be predicted.

[0016] In a third aspect, the present application provides an electronic device comprising a memory and a processor, and computer instructions stored in the memory and running on the processor, wherein when the computer instructions are run by the processor, the method of the first aspect is completed.

[0017] In a fourth aspect, the present application provides a computer readable storage medium for storing computer instructions, wherein when the computer instructions are executed by a processor, the method of the first aspect is completed.

[0018] In a fifth aspect, the present application provides a computer program product comprising a computer program, wherein when the computer program is executed by a processor, the method of the first aspect is completed.

[0019] Compared with the prior art, the present application has the following beneficial effects: The present application proposes a rock-embedded single pile horizontal bearing capacity prediction method and system that fuses mesoscopic physical mechanism and deep learning technology, constructs a numerical sample library of rock-embedded single pile horizontal loading containing multiple working conditions through FDEM numerical simulation, extracts mechanical state variables representing the physical state of the pile-rock system from the FDEM numerical simulation results, thereby constructs a training set based on the pile top displacement, pile top load and mechanical state variables of each loading step; constructs a proxy model architecture combining physical kernel and residual learning, embeds the physical law in the artificial intelligence model in a hard constraint manner, takes the pile body design parameters, rock mass design parameters and target pile top displacement as inputs, and takes the pile top load and mechanical state variables as outputs, and makes the predicted values output by the proxy model approach the FDEM numerical simulation values through optimizing the loss function, thereby fundamentally solving the problem of insufficient physical consistency of pure data-driven AI models in extrapolation prediction.

[0020] Advantages of the additional aspects of the application will become apparent in the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.

[0022] Figure 1 A flow chart of a rock-embedded single pile horizontal bearing capacity prediction method for digital mechanics twinning provided for embodiment 1 of the present application; Figure 2 A prediction result rendering chart in the case provided for embodiment 1 of the present application; Figure 3 A FDEM simulation result chart in the case provided for embodiment 1 of the present application. DETAILED DESCRIPTION

[0023] The present application will be further described below in combination with the drawings and embodiments.

[0024] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0025] It should be noted that the terms used herein are only for the purpose of describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form, and in addition, it should be understood that the terms "comprise" and "include" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] The embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0027] Embodiment 1 The present embodiment provides a rock-embedded single pile horizontal bearing capacity prediction method for digital mechanics twinning, which is characterized by an innovative physical mechanism dataization and data modeling intelligentization path to build a fast, accurate and physically credible proxy model.

[0028] As Figure 1 shown, comprising the following steps: By FDEM numerical simulation, a numerical sample library of rock-embedded single pile horizontal loading containing various working conditions is constructed, and from the FDEM numerical simulation results, the mechanical state variables representing the physical state of the pile-rock system are extracted, thereby constructing a training set based on the pile top displacement, pile top load and mechanical state variables of each loading step; The proxy model is constructed with the pile body design parameters, rock mass design parameters and target pile top displacement as input, and the pile top load and mechanical state variables as output, and the training set is used to train the proxy model, and the loss function is optimized to make the predicted value of the proxy model approach the FDEM numerical simulation value; According to the pile foundation design parameters to be predicted, the trained proxy model is used to obtain the horizontal load-displacement response curve and the mechanical state variable evolution process.

[0029] The method of the present embodiment will be described in detail below.

[0030] S1: High-fidelity finite element-discrete element coupling (FDEM) numerical simulation and construction of numerical sample library.

[0031] Specifically: A three-dimensional rock-embedded single pile numerical model accurately simulating the cracking and crushing process of rock is established by the finite element-discrete element coupling (FDEM) method.

[0032] A large number of numerical simulation samples covering different working conditions are generated by systematically changing the pile diameter, rock-embedded depth, rock elastic modulus, cohesion, internal friction angle and other key design parameters.

[0033] A horizontal displacement load is applied to each numerical simulation sample to finely simulate the entire process from the initial linear, nonlinear to failure, and the horizontal load-displacement curve, pile internal force, and rock mass stress, strain and damage field data are recorded to form a high-fidelity numerical sample library.

[0034] S2: From the FDEM simulation results, extract and calculate the key mechanical state variables for representing the physical state of the pile-rock system, aiming to refine the massive, unstructured field data into low-dimensional, structured and physically meaningful features.

[0035] Specifically: 1. Spatial zoning: According to the pile-rock interaction mechanism, the surrounding pile rock mass is divided into continuous control intervals along the embedded depth of the pile; (for example, 0.5 times the pile diameter as one control interval).

[0036] 2. Field variable integral average: For each loading step, traverse all rock mass elements of the FDEM, determine its control interval according to the rock mass element center coordinate; Then, calculate the volume-weighted average of the field variables of all rock mass elements in each control interval; the field variables include damage factor D and plastic strain ; Thus, the damage factor vector along the depth distribution at each loading step is obtained And the plastic strain vector .

[0037] 3. Pile response extraction: at the corresponding depth of each control interval, extract the pile bending moment value M at the corresponding depth of each control interval to form the pile bending moment vector .

[0038] 4. Construct a structured sequence: align the pile top displacement U, pile top load H of each loading step with the above three key mechanical state vectors (the key mechanical state variables are the damage factor vector, plastic strain vector and pile bending moment vector along the depth direction), and finally construct a structured state evolution sequence for each simulation: The entire numerical sample library is thus converted into a data set that can be used for machine learning.

[0039] S3: Based on the paradigm of the fusion of physical mechanism and artificial intelligence, a proxy model embedded with physical information is constructed, which is a deep learning network embedded with physical information. It adopts a multi-task architecture combining physical kernel and residual learning. The core idea is that the physical kernel provides the basic solution, and AI learns the correction. The pile body parameters, rock mass parameters and target displacement are input, and the pile top load and key mechanical state variables are output.

[0040] Specifically, it includes: 1. Physical kernel layer: used to receive pile design parameters and rock mass design parameters, and calculate preliminary physical prediction results based on a simplified physical model, including pile top load physical prediction value And the pile bending moment physical prediction value distributed along the pile body.

[0041] This layer is a differentiable parameterized simplified physical model, such as a beam-spring model based on the Winkler foundation assumption or a p-y curve model; receives pile design parameters (such as diameter, rock-embedded depth and pile body elastic modulus) and rock mass design parameters (such as rock mass elastic modulus, cohesion and internal friction angle), and calculates a preliminary, physically reasonable prediction result for the target pile top displacement U , including the pile top load physical prediction value And the pile bending moment physical prediction value This layer ensures that the model gives predictions that are consistent with the physics even in unknown regions.

[0042] 2. Residual learning branch: This branch is a deep learning network, such as a multilayer perceptron, which is unique in that the learning objective is not the full response, but the residual between the FDEM simulation values (pile top load simulation values and pile body bending moment simulation values ) and the physical kernel layer prediction results, i.e., pile top load residual and pile body bending moment residual , and simultaneously learns key mechanical state variables; Its inputs include pile design parameters, rock mass design parameters, target pile top displacement, and soil reaction force calculated by the physical kernel layer to provide rich physical context information; the outputs are residuals , and mechanical state variable predictions, i.e., damage factor prediction and plastic strain prediction .

[0043] 3. Multi-task output and fusion: The final prediction output of the surrogate model includes: pile top load prediction ; pile body bending moment prediction ; and physical and mechanical state variable predictions and .

[0044] This design makes the AI only need to learn the deviation of the complex physical process, greatly reducing the learning difficulty, and built-in physical consistency.

[0045] S4: Multi-objective loss function and physical constraint training; use the numerical sample set to train the surrogate model, and make the surrogate model prediction value approach the FDEM simulation value by optimizing the loss function.

[0046] Specifically: The loss function Loss is a multi-task weighted loss, and its expression is: ; Where, , , and are the mean square error losses of the pile top load, pile body bending moment, damage factor, and plastic strain prediction values, respectively; , , , and are the weight coefficients. , , and These are the actual values ​​of pile top load, pile bending moment, damage factor, and plastic strain, respectively. This is a physical constraint penalty term used to force the model to comply with deeper physical laws.

[0047] Among them, physical constraint penalty item At least including: Equilibrium Constraints: Based on Predicted Values ​​of Pile Bending Moment Distribution Calculate soil reaction And check the predictions Does it satisfy the static equilibrium equations? .

[0048] Irreversible constraint: Forced damage factor prediction value The displacement increases monotonically with loading.

[0049] Forced damage factor prediction value Predicted bending moment of pile body or soil reaction force Negative correlation.

[0050] These constraints transform physical laws from soft constraints to hard constraints, ensuring the rationality of extrapolation predictions at the model architecture level.

[0051] S5: Input the design parameters of the rock-socketed single pile to be predicted (pile design parameters and rock mass design parameters) into the trained surrogate model to obtain its complete horizontal load-displacement response curve and the distribution and evolution process of damage factor, plastic strain and pile bending moment along the pile body.

[0052] Through the above steps, this embodiment successfully constructs a digital-mechanical twin prediction method that combines physical reliability and computational efficiency. The following detailed description of these steps, using a basic implementation case, further illustrates the entire process of this method. This case aims to clearly demonstrate the entire process, therefore using laboratory-scale model parameters; however, its principles and methods are applicable to full-scale engineering applications.

[0053] Case objective: To predict the horizontal load-displacement (HU) response curve and internal mechanical state variables of a rock-embedded monopile of a specific size under given rock design parameters.

[0054] S1: FDEM numerical simulation and data generation.

[0055] 1. Model parameter settings: Pile design parameters: Pile diameter d = 0.1m, rock embedding depth Elastic modulus of pile .

[0056] Rock mass design parameters: Brittle rock parameters are adopted, including the rock mass elastic modulus. Cohesion c = 1MPa, internal friction angle 40°.

[0057] Loading: Apply horizontal displacement to the top of the pile until... U = 10mm.

[0058] 2. Construct a sample library: Around the aforementioned benchmark parameters, 100 sample points are generated within a certain range of fluctuation (e.g., , , wait).

[0059] Each sample was subjected to an FDEM simulation, which took approximately several hours per simulation. In this example, a total of 100 simulations were performed, generating a numerical sample library containing 100 samples.

[0060] S2: Extract key mechanical state variables.

[0061] Take a simulation as an example: 1. Spatial partitioning: The embedded segment is divided into There are several intervals, each with a depth of 0.05m.

[0062] 2. Field variable averaging: For the fourth interval (depth 0.15-0.20m), in displacement U When the damage is 5mm, the damage values ​​of all rock mass elements within this interval are statistically analyzed, and their volume-weighted average is calculated. D 4. Similarly, calculate the average plastic strain in this interval. Extract the pile bending moment at the midpoint depth of the interval.

[0063] 3. Constructing the sequence: Repeat this process for all 10 intervals and 100 loading steps to ultimately generate a sequence containing... The state sequence.

[0064] S3: Building and training agent models.

[0065] 1. Physical kernel layer settings: Select the Winkler foundation beam model as the physical kernel. Its foundation reaction coefficient... k The value is estimated from the input rock modulus. Given a displacement, the model quickly calculates the physical prediction of the pile bending moment. Physical prediction of pile top load .

[0066] 2. Residual learning branch setup: Construct a multilayer perceptron (MLP), whose input layer includes: pile diameter d Rock embedding depth L r Rock elastic modulus E r Target pile top displacement U and the ground reaction force calculated by the physical kernel p ( z The MLP outputs four parts: pile top load residuals. Pile body bending moment residual and physical and mechanical state variables and .

[0067] 3. Training: Approximately 100,000 structured data points (100 samples * 1000 loading steps) generated from 100 simulations were divided into training and test sets in an 8:2 ratio. The Adam optimizer was used with a multi-task loss function (where the physical constraint weights are...). (Set to 0.1) Train the surrogate model.

[0068] S4: Implement prediction and verification.

[0069] 1. Input: Predict a new case not seen in the training set: pile diameter d =0.095m, embedment depth rock modulus .

[0070] 2. Prediction: Input this set of parameters into the trained surrogate model, and output the HU curve, the pile bending moment M(z) along the pile depth, and the rock mass damage distribution D(z) along the pile depth. For example... Figure 2 The image shown is a rendering obtained after the generated strain field prediction is transmitted to a 3D visualization platform via a communication protocol.

[0071] 3. Verification: Figure 3 The figure shown is the result of FDEM simulation. The FDEM simulation result is used as a verification benchmark to compare the prediction accuracy.

[0072] Example 2 This embodiment provides a system for predicting the horizontal bearing capacity of a rock-socketed monopile using digital mechanical twins, including: The numerical simulation module is configured to construct a numerical sample library containing various working conditions of horizontal loading of rock-socketed monopile through FDEM numerical simulation, and extract mechanical state variables that characterize the physical state of the pile-rock system from the FDEM numerical simulation results, thereby constructing a training set based on the pile top displacement, pile top load and mechanical state variables of each loading step. The model building and training module is configured to build a proxy model with pile design parameters, rock mass design parameters and target pile top displacement as inputs, and pile top load and mechanical state variables as outputs. The proxy model is trained using a training set, and the predicted values ​​output by the proxy model are made to approximate the FDEM numerical simulation values ​​by optimizing the loss function. The prediction module is configured to use a trained surrogate model based on the design parameters of the pile foundation to be predicted to obtain the horizontal load-displacement response curve and the evolution process of mechanical state variables.

[0073] It should be noted that the above modules correspond to the steps described in Embodiment 1, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should also be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer-executable instructions.

[0074] In further embodiments, the following is also provided: An electronic device includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, wherein the computer instructions, when executed by the processor, perform the method described in Embodiment 1. For brevity, further details are omitted here.

[0075] It should be understood that in this embodiment, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0076] Memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of memory may also include non-volatile random access memory. For example, memory may also store information about the device type.

[0077] A computer-readable storage medium for storing computer instructions, which, when executed by a processor, perform the method described in Embodiment 1.

[0078] The method in Example 1 can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor. The software modules can reside in readily available storage media in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not provided here.

[0079] A computer program product includes a computer program that, when executed by a processor, implements the method described in Embodiment 1.

[0080] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, which execute in a device on a target real or virtual processor to perform the processes / methods described above. Typically, program modules include routines, programs, libraries, objects, classes, components, data structures, etc., that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of program modules can be combined or divided among program modules as needed. The machine-executable instructions for the program modules can execute within a local or distributed device. In a distributed device, the program modules can reside in both local and remote storage media.

[0081] The computer program code used to implement the methods of the present invention may be written in one or more programming languages. This computer program code may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the computer or other programmable data processing device, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a computer, partially on a computer, as a stand-alone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0082] In the context of this invention, computer program code or related data may be carried by any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and the like. Examples of signals may include electrical, optical, radio, sound, or other forms of propagation signals, such as carrier waves, infrared signals, etc.

[0083] Those skilled in the art will recognize that the units and algorithm steps described in connection with the various examples of this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0084] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for predicting the horizontal bearing capacity of a rock-embedded monopile using digital mechanical twins, characterized in that, include: Through FDEM numerical simulation, a numerical sample library of horizontal loading of rock-socketed monopile with various working conditions is constructed. Mechanical state variables characterizing the physical state of the pile-rock system are extracted from the FDEM numerical simulation results. Thus, a training set is constructed based on the pile top displacement, pile top load and mechanical state variables of each loading step. A surrogate model is constructed with pile design parameters, rock mass design parameters, and target pile top displacement as inputs, and pile top load and mechanical state variables as outputs. The surrogate model is trained using a training set, and the predicted values ​​output by the surrogate model are made to approximate the FDEM numerical simulation values ​​by optimizing the loss function. Based on the pile foundation design parameters to be predicted, a trained surrogate model is used to obtain the horizontal load-displacement response curve and the evolution process of mechanical state variables.

2. The method for predicting the horizontal bearing capacity of a rock-embedded single pile using digital mechanical twins as described in claim 1, characterized in that, The mechanical state variables include damage factor, plastic strain, and pile bending moment. After aligning the pile top displacement and pile top load with the three mechanical state vectors for each loading step, a structured state evolution sequence is constructed for each FDEM numerical simulation.

3. The method for predicting the horizontal bearing capacity of a rock-embedded monopile using digital mechanical twins as described in claim 1, characterized in that, The process of extracting mechanical state variables includes: Along the direction of the pile's embedment depth, the surrounding rock mass is divided into... A continuous control interval; For each loading step, traverse all rock mass elements in the FDEM and determine the control interval based on the center coordinates of the rock mass elements; Calculate the volume-weighted average of the field variables for all rock mass elements within each control interval. The field variables include damage factor and plastic strain. Also, extract the pile bending moment value at the corresponding depth for each control interval.

4. The method for predicting the horizontal bearing capacity of a rock-embedded single pile using digital mechanical twins as described in claim 1, characterized in that, The surrogate model includes a physical kernel layer and a residual learning branch; The physical kernel layer takes the pile design parameters and rock mass design parameters as inputs and outputs the physical prediction values ​​of the pile top load and the physical prediction values ​​of the pile bending moment distributed along the pile body. The residual learning branch takes the pile design parameters, rock mass design parameters, target pile top displacement, and soil reaction force calculated from the physical core layer as inputs, and outputs the pile top load residual, pile body bending moment residual, damage factor prediction value, and plastic strain prediction value. The pile top load residual is the difference between the simulated pile top load value and the physical prediction value of the pile top load, and the pile body bending moment residual is the difference between the simulated pile body bending moment value and the physical prediction value of the pile body bending moment.

5. The method for predicting the horizontal bearing capacity of a rock-embedded monopile using digital mechanical twins as described in claim 1, characterized in that, The loss function is: ； in, , , and These are the predicted values ​​of the pile top load. Predicted bending moment of pile body Damage factor prediction value and plastic strain prediction values The mean squared error loss; , , , and These are the weighting coefficients; , , and These are the actual values ​​of pile top load, pile bending moment, damage factor, and plastic strain, respectively. This is a physical constraint penalty term.

6. The method for predicting the horizontal bearing capacity of a rock-embedded monopile using digital mechanical twins as described in claim 5, characterized in that, Physical constraint penalty item include: Calculation of soil reaction force based on predicted pile bending moment ,and Satisfies the static equilibrium equations: ; Damage factor predicted value The displacement increases monotonically with loading; Damage factor predicted value Predicted bending moment of pile body or soil reaction force Negative correlation.

7. A system for predicting the horizontal bearing capacity of a rock-embedded monopile for digital mechanical twinning, characterized in that, include: The numerical simulation module is configured to construct a numerical sample library containing various working conditions of horizontal loading of rock-socketed monopile through FDEM numerical simulation, and extract mechanical state variables that characterize the physical state of the pile-rock system from the FDEM numerical simulation results, thereby constructing a training set based on the pile top displacement, pile top load and mechanical state variables of each loading step. The model building and training module is configured to build a proxy model with pile design parameters, rock mass design parameters and target pile top displacement as inputs, and pile top load and mechanical state variables as outputs. The proxy model is trained using a training set, and the predicted values ​​output by the proxy model are made to approximate the FDEM numerical simulation values ​​by optimizing the loss function. The prediction module is configured to use a trained surrogate model based on the design parameters of the pile foundation to be predicted to obtain the horizontal load-displacement response curve and the evolution process of mechanical state variables.

8. An electronic device, characterized in that, It includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, which, when executed by the processor, perform the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, Used to store computer instructions, which, when executed by a processor, perform the method described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program, which, when executed by a processor, implements the method described in any one of claims 1-6.

Images