A rectangular anti-slide pile hole forming method and device based on multi-physical field coupling

Abstract

The application provides a rectangular anti-slide pile hole forming method and device based on multi-physical field coupling, and relates to the technical field of anti-slide pile construction. The method comprises the following steps: obtaining geological physical information and stratum structure data; performing multi-physical field coupling drilling simulation based on the geological physical information and the stratum structure data to obtain a drill-ground coupling model; applying control parameters to the drill-ground coupling model, combining with drill bit parameters to perform dynamic drilling simulation and generate a multi-dimensional data set; performing hybrid training of the multi-dimensional data set and actual measurement samples, performing scheme prediction through a multi-layer feedforward neural network, obtaining an optimized drilling scheme; and performing anti-slide pile hole forming verification and construction based on the optimized drilling scheme to obtain an optimal anti-slide pile hole forming scheme. The application solves the problem that the rectangular section anti-slide pile cannot be widely applied and cannot exert its performance under complex geological conditions.

Description

Technical Field

[0001] This invention relates to the field of anti-slide pile construction technology, and more specifically, to a method and apparatus for drilling rectangular anti-slide piles based on multi-physics field coupling. Background Technology

[0002] In existing anti-slide pile construction technologies, manually excavated bored piles and circular drill piles are the most common. While these methods can meet the bearing capacity requirements in conventional strata, they suffer from poor borehole stability, low construction accuracy, and weak adaptability when encountering deep overburden layers and high bearing capacity demands. In contrast, rectangular cross-section anti-slide piles have significant advantages in anti-slide stability, uniform stress distribution, and material utilization, effectively improving the overall safety and economy of slope and pile foundation structures. However, there is currently a lack of systematic research on the matching relationship between the equipment structural parameters, drilling methods, and stratum characteristics of rectangular cross-section anti-slide piles. Furthermore, there is a lack of optimized construction techniques adapted to different geological conditions, resulting in the limited application and effectiveness of rectangular cross-section anti-slide piles in complex geological conditions.

[0003] Therefore, there is an urgent need for a method and device for drilling rectangular anti-slide piles based on multi-physics coupling, which solves the problem that rectangular cross-section anti-slide piles cannot be widely used and their effectiveness cannot be fully realized under complex geological conditions. Summary of the Invention

[0004] The purpose of this invention is to provide a method and apparatus for drilling rectangular anti-slide piles based on multi-physics field coupling, so as to improve the above-mentioned problems. To achieve the above objective, the technical solution adopted by this invention is as follows:

[0005] In a first aspect, this application provides a method for drilling rectangular anti-slide piles based on multi-physics coupling, including:

[0006] To acquire geophysical information and stratigraphic data;

[0007] Based on the geophysical information and the stratigraphic structure data, a multiphysics field coupled drilling simulation is performed to obtain a drilling-geometry coupled model.

[0008] Control parameters are applied to the drilling-geology coupling model, and dynamic drilling simulation is performed in combination with drill bit parameters to generate a multidimensional dataset.

[0009] The multidimensional dataset is trained using a combination of simulation and experimental samples. A multi-layer feedforward neural network is then used to predict the drilling scheme, resulting in an optimized drilling scheme.

[0010] Based on the optimized drilling scheme, the anti-slide pile hole formation was verified and constructed to obtain the optimal anti-slide pile hole formation scheme.

[0011] Secondly, this application also provides a rectangular anti-slide pile drilling device based on multi-physics coupling, comprising:

[0012] The acquisition module is used to acquire geological and physical information and stratigraphic structure data;

[0013] The simulation module is used to perform multiphysics coupled drilling simulation based on the geophysical information and the stratigraphic structure data to obtain a drilling-geometry coupled model.

[0014] The simulation module is used to apply control parameters to the drilling-geological coupling model, combine the drill bit parameters to perform dynamic drilling simulation, and generate a multidimensional dataset.

[0015] The prediction module is used to perform mixed training of simulation and measured samples on the multidimensional dataset, and to predict the scheme through a multi-layer feedforward neural network to obtain an optimized drilling scheme.

[0016] The construction module is used to verify and construct the anti-slide pile hole formation based on the optimized drilling scheme, so as to obtain the optimal anti-slide pile hole formation scheme.

[0017] The beneficial effects of this invention are as follows:

[0018] This invention utilizes multiphysics-coupled drilling simulation to realistically recreate the interaction between the drill bit and complex formations, overcoming the fuzzy judgments of formation responses made by traditional empirical methods. It achieves visualized and quantitative analysis of borehole trajectory evolution, borehole wall stability degradation, and the sensitivity of drilling parameters. Furthermore, dynamic drilling simulation identifies sections prone to borehole collapse, diameter reduction, or deviation in advance, thereby optimizing drill bit selection, rotation speed, drilling pressure, and mud properties, reducing rework and concrete waste caused by borehole instability. Then, using simulation and field measurement samples for training, real-time feedback of on-site monitoring data continuously refines the drilling plan, forming a closed-loop optimization mechanism where the more drilling, the more accurate the results. In summary, this invention solves the problem of the limited application and effectiveness of rectangular cross-section anti-slide piles under complex geological conditions.

[0019] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1This is a schematic diagram of the process for forming a rectangular anti-slide pile based on multi-physics coupling, as described in an embodiment of the present invention.

[0022] Figure 2 This is a schematic diagram of the bullet-shaped drill bit in the drilling rig structural features described in this embodiment of the invention;

[0023] Figure 3 This is a schematic diagram of the toothed drill bit in the drilling rig structural features described in this embodiment of the invention;

[0024] Figure 4 This is a schematic diagram of the airfoil drill bit in the drilling rig structural features described in this embodiment of the invention;

[0025] Figure 5 This is a schematic diagram of the rectangular anti-slide pile drilling equipment based on multi-physics coupling as described in an embodiment of the present invention.

[0026] The diagram is labeled as follows: 800, Rectangular anti-slide pile drilling equipment based on multi-physics coupling; 801, Processor; 802, Memory; 803, Multimedia component; 804, I / O interface; 805, Communication component. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0028] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0029] Example 1:

[0030] This embodiment provides a method for drilling rectangular anti-slide piles based on multi-physics coupling.

[0031] See Figure 1 The figure shows that the method includes steps S1 to S5, including:

[0032] S1: Obtain geophysical information and stratigraphic data;

[0033] In this step, the geophysical information is collected by using three-dimensional terrain scanning, UAV mapping, or lidar technology to collect the topography, geology, underground structural surfaces, and physical and mechanical parameters of the soil and rock mass in the target area. This information is used to define the boundaries of the stratigraphic structure, layering characteristics, and material parameter distribution, ensuring that the subsequent geometric morphology, physical properties, and structural surface characteristics of the soil and rock mass are consistent with the actual engineering conditions.

[0034] The stratigraphic structure data was obtained by stratifying and sampling the soil and rock layers in the target area and conducting laboratory tests. The basic physical and mechanical parameters of the soil and rock were determined, and the properties of the soil and rock at different depths and layers were assigned regional values.

[0035] S2: Based on the geophysical information and the stratigraphic structure data, perform multiphysics field coupled drilling simulation to obtain a drilling-geometry coupled model;

[0036] In this step, multiphysics coupled drilling simulation is used to realistically recreate the interaction between the drill bit and complex formations. This eliminates the fuzzy judgment of formation response by traditional empirical methods and enables visualized quantitative analysis of borehole trajectory evolution, borehole wall stability degradation process, and drilling parameter sensitivity, providing a scientific basis for real-time control and optimization of drilling parameters.

[0037] To clarify the specific method for obtaining the drilling-coupling model, step S2 includes S21 to S24, specifically:

[0038] S21: Based on the target site geometry in the geophysical information and the stratigraphic influence range in the stratigraphic structure data, a numerical geometric model is constructed to obtain the numerical geometric model;

[0039] To clarify the specific method for obtaining the numerical geometric model, step S21 includes S211 to S213, specifically:

[0040] S211: Determine the spatial boundary based on the target site geometry in the geophysical information and the stratigraphic influence range in the stratigraphic structure data, and generate a three-dimensional coupled model;

[0041] In this step, the core area of ​​drilling disturbance is identified by extracting the actual surface elevation, slope morphology, potential slip zone depth, and stratigraphic structure of the target slope, combined with remote sensing mapping, LiDAR point cloud data, and geological profile information. Based on this, the calculation area is expanded in the form of an extended buffer zone. The buffer distance is determined comprehensively based on stratigraphic lithology, structural complexity, and numerical model type to effectively reduce the interference of boundary effects on the drilling mechanical response. Using the WGS-84 coordinate system as a reference, a three-dimensional coupled model covering key geological interfaces such as the surface, subsurface interface, fault / joint surfaces, and groundwater level is constructed.

[0042] S212: Discretize the three-dimensional coupled model according to the geometric dimensions of the target site to obtain a numerical grid structure;

[0043] In this step, the three-dimensional coupled model is discretized according to the geometric dimensions of the target site. The discretization method includes block partitioning, particle filling, or hybrid mesh partitioning. The numerical grid structure is used to carry the subsequent assignment of geotechnical parameters and stress field calculation.

[0044] S213: Apply asymmetric constraint boundaries to the numerical grid structure based on the actual geostress field and preset geological boundary conditions to obtain a numerical geometric model.

[0045] In this step, a fixed constraint is applied to the bottom of the numerical grid structure according to the actual geostress field and the preset geological boundary conditions, a horizontal displacement restriction is applied to the lateral boundary, and the top boundary is set to a free state, so that the initial stress state of the numerical grid structure is consistent with the field geostress environment.

[0046] S22: Based on the numerical geometric model, the borehole area is determined. By assigning material property values ​​and dividing the borehole area into regional parameters, a geomechanical model is obtained.

[0047] To clarify the specific method for obtaining the geomechanical model, step S22 includes S221 to S225, which specifically include:

[0048] S221: Based on the numerical geometric model, the drilling region is determined, and the drilling space is obtained by performing cavitation of the grid cells in the drilling region.

[0049] In this step, the drilling location and trajectory of the proposed anti-slide piles are determined based on a numerical geometric model. The grid cells in the drilling area are then emptied to release their spatial volume, forming an initial drilling channel. To avoid the influence of boundary effects on the borehole periphery response, a certain buffer zone is extended outward from the initial drilling channel, ultimately obtaining the drilling space used to simulate drilling disturbances.

[0050] S222: Perform particle system modeling on the borehole space to generate rock mass particle structure;

[0051] In this step, a non-uniform particle size aggregate is generated within the borehole space and its surrounding influence zone. Particle size distribution is controlled using the radius expansion method, and irregular particle morphologies are constructed using clustering technology to accurately reflect the microstructure of the natural rock mass. The particle system should cover the main stress-affected zone around the borehole to subsequently capture stress redistribution and local fracturing behavior during drilling.

[0052] S223: Input the geophysical and mechanical parameters of the soil and rock in the geophysical information into the rock mass particle structure to divide the particle radius interval and determine the spatial distribution density of the particles, and obtain the physical feature mapping result;

[0053] In this step, a particle model is introduced based on the aforementioned geophysical and mechanical parameters. Particle radius ranges are divided according to stratigraphic stratification characteristics, and corresponding spatial distribution densities are set. Through macro-micro parameter calibration, the micromechanical parameters of the interparticle contact model are determined, ensuring that the macroscopic mechanical response of the particle system is consistent with laboratory test results. Ultimately, a physical characteristic mapping result reflecting stratigraphic differences is formed.

[0054] S224: Perform initial geostress balance calculations on the physical feature mapping results to obtain a stable stress state;

[0055] In this step, the physical feature mapping results are used to perform initial equilibrium calculations to start the particle flow model, eliminating unreasonable overlaps, gaps, and unbalanced forces generated during particle generation, so that the system reaches a static equilibrium state under its own weight and boundary constraints, and obtains a stable initial stress state.

[0056] S225: Based on the stable stress state and the rock mass constitutive relationship in the stratigraphic structure data, a geomechanical model is constructed to obtain the model.

[0057] In this step, the particle system based on the stable stress state is coupled with the rock mass constitutive relationship in the stratigraphic structure data, and a unified geomechanical model is established using a discrete-continuous coupling method. This geomechanical model simultaneously possesses the ability to simulate local fracturing of discrete particles and the ability to analyze the overall deformation of continuous media, providing a physical basis for subsequent drilling-geological interaction simulations.

[0058] S23: Construct a geometric model of the drill bit based on the structural features and size parameters of the drilling rig in the geophysical information;

[0059] In this step, a drill bit geometric model is established based on the drilling rig structural features and drilling rig size parameters in the geophysical information. The drill bit geometric model includes a complete numerical simulation system of formation distribution, material properties, contact characteristics and drill bit loading parameters. The drill bit geometric model is used for subsequent simulation of contact interaction with the formation.

[0060] S24: Based on the numerical geometric model, the geomechanical model and the drill bit geometric model, spatial matching and contact interface coupling are performed to establish a drilling-geometry coupling model.

[0061] In this step, the drilling-ground coupling model is a drilling rig-formation coupling calculation model. The drilling-ground coupling model simulates the entire drilling process by inputting drilling rig operating parameters and records the key responses of the drill bit and the formation during the simulation.

[0062] S3: Apply control parameters to the drilling-geological coupling model, combine the drill bit parameters to perform dynamic drilling simulation, and generate a multidimensional dataset;

[0063] In this step, dynamic drilling simulation is performed in conjunction with drill bit parameters to identify sections prone to hole collapse, narrowing, or deviation in advance. This allows for optimization of drill bit selection, rotation speed and drilling pressure, as well as mud properties, reducing rework and concrete waste caused by unstable borehole walls.

[0064] To clarify the specific method for obtaining the multidimensional dataset, step S3 includes S31 to S36, specifically:

[0065] S31: Obtain drilling rig parameters;

[0066] In this step, the drilling rig parameters include feed rate, angular velocity, rotational speed, drill bit type, drill bit geometry parameters, and drill bit entry angle into the rock.

[0067] S32: Apply drilling control parameters to the drilling-ground coupling model, and perform group modeling based on drill bit type and formation characteristics to obtain grouped drilling rig models;

[0068] In this step, drilling control parameters are applied to the drilling-geometry coupling model. After applying the drilling control parameters, the drilling-geometry coupling model is grouped and modeled according to the drill bit type and formation characteristics. The drill bit-rock contact area is locally meshed. The drill bit template is assembled with the corresponding formation section to ensure that the initial contact surface fits, thus forming a grouped drilling rig model.

[0069] S33: Based on the drilling rig parameters and the grouped drilling rig model, assign real construction parameters to the drill bit, and perform time-domain discretization by a preset fixed time step to obtain the drill bit motion trajectory;

[0070] In this step, the drilling rig parameters, such as the propulsion speed and angular velocity, are applied as boundary conditions to the drill bit model. A fixed time step is used for time-domain discretization to update the drill bit position. The stress distribution on the drill bit surface, the hole wall displacement, and the stress and elastoplastic states of the zone region are recorded to generate the trajectory, thus obtaining the drill bit motion trajectory.

[0071] S34: Calculate the contact area between the drill bit and the formation in real time based on the drill bit's movement trajectory, and obtain the drilling space distribution by updating the contact boundary conditions;

[0072] In this step, based on the drill bit's movement trajectory, the drill bit's current position and geometry, as well as the contact detection algorithm, determine whether the drill bit surface is in contact with the formation unit, re-identify the contact area, and obtain the drilling space distribution by adjusting the contact boundary conditions.

[0073] S35: Based on the drill bit motion parameters and preset contact states in the drilling rig parameters, monitor the stress distribution on the drill bit surface hourly and output the monitoring data;

[0074] S36: Integrate the drill bit movement trajectory, the drilling spatial distribution, and the monitoring data to generate a multidimensional dataset.

[0075] S4: Perform mixed training of simulation and measured samples on the multidimensional dataset, and predict the scheme through a multi-layer feedforward neural network to obtain an optimized drilling scheme;

[0076] In this step, simulation and actual test sample training are used to provide real-time feedback of on-site drilling monitoring data, continuously correct the drilling plan, and form an online closed-loop optimization mechanism that makes the more you drill, the more accurate the results and the more accurate the model.

[0077] To clarify the specific method for obtaining the optimized drilling plan, step S4 includes S41 to S45, specifically:

[0078] S41: Preprocess the simulated samples and measured samples in the multidimensional dataset to obtain a training feature set;

[0079] In this step, the mixed dataset of simulated samples and measured samples in the multidimensional dataset is uniformly encoded and normalized, and principal component analysis is used to reduce the dimensionality of features and construct a training feature set.

[0080] S42: Based on the training feature set and the multi-layer feedforward neural network, the initial neural network model is obtained by jointly training and constructing the simulation and measured data in the training feature set.

[0081] In this step, the multilayer feedforward neural network includes an input layer, a hidden layer, and an output layer. It is jointly trained using a mixture of simulation and experimental datasets, and employs fold cross-validation and early stopping mechanisms to prevent overfitting during joint training with the mixed datasets.

[0082] The input layer consists of formation mechanical parameters, void ratio, drill bit rotation speed, thrust, and rock penetration angle from the multidimensional dataset. The hidden layer adopts a 2-4 layer fully connected structure, with the number of nodes in each layer adaptively set according to the sample size. The ReLU activation function is selected to capture nonlinear feature relationships. The output layer includes drill bit stress level, borehole wall displacement amplitude, damage zone range, or borehole wall stability index.

[0083] S43: Input the real-time geological parameters of the target formation into the initial neural network model to predict the response results under different combinations of drilling parameters, and combine the genetic algorithm to perform multi-objective optimization to obtain candidate drilling schemes;

[0084] In this step, the real-time geological parameters of the target formation are input into the initial neural network model to predict the response under different combinations of drilling parameters. A multi-objective optimization function is constructed by combining a genetic algorithm, and the Pareto front is solved by the NSGA-II genetic algorithm to generate candidate drilling schemes.

[0085] S44: Based on the feedback learning mechanism, the initial neural network model is dynamically updated and self-learned to evolve, resulting in an optimized neural network model;

[0086] In this step, the model is dynamically updated and evolved based on a feedback learning mechanism. Real-time collected data is compared with the model's prediction results; if the error exceeds a set threshold, a model update process is triggered. During the update, the weights of the initial neural network model are fine-tuned according to a preset strategy to generate an optimized neural network model. The optimized neural network model exhibits enhanced adaptability and prediction accuracy in the field environment.

[0087] S45: Input the candidate drilling scheme into the optimized neural network model to predict the drilling response and obtain the optimized drilling scheme.

[0088] In this step, the candidate drilling schemes are input into the optimization neural network model, and response prediction and stability evaluation are performed on each scheme. Based on safety, efficiency and / or cost, multiple indicators are weighed to select the optimal compromise scheme and output the final optimized drilling scheme.

[0089] The optimized drilling scheme includes key parameters such as drill bit type (single-edged, double-edged, toothed drill bit), rock entry angle, rotational speed, and axial thrust.

[0090] S5: Based on the optimized drilling scheme, verify and construct the anti-slide pile hole formation to obtain the optimal anti-slide pile hole formation scheme.

[0091] To clarify the specific method for obtaining the optimal pile drilling scheme, step S5 includes S51 to S54, specifically:

[0092] S51: Based on the optimized drilling scheme, the formation attribute parameters of the target formation are input into a multi-layer feedforward neural network for multi-objective regression and classification joint operation, and the drill bit combination scheme is output.

[0093] In this step, the physical and mechanical parameters of the target formation are first standardized based on the optimized drilling scheme and used as input feature vectors. Then, these input feature vectors are fed into an optimized neural network model for multi-task learning.

[0094] The multi-task learning includes a regression task to predict key response indicators of the drill bit during the drilling process and a classification task to identify possible failure modes during drilling, generating several candidate drill bit combination schemes.

[0095] S52: Based on the drill bit combination scheme, conduct on-site drilling operations under the same or similar geological conditions to form a verification dataset;

[0096] In this step, on-site drilling operations are carried out based on the drill bit combination scheme, specifically by selecting test sections or pilot holes that are highly consistent with the geological conditions of the target strata. Multi-source monitoring data are collected simultaneously during construction to build a validation dataset.

[0097] S53: Compare the verification dataset with the preset hole formation quality target to generate difference analysis results;

[0098] In this step, the verification dataset is compared item by item with the preset hole-forming quality target to conduct a multi-dimensional difference analysis and generate the difference analysis results. The multi-dimensional difference analysis includes quantitative error analysis, failure mode identification bias, parameter sensitivity tracing, and engineering acceptability assessment.

[0099] S54: Based on the difference analysis results, the weights of the multilayer feedforward neural network are dynamically updated and a scheme is generated through an online transfer learning mechanism and the validation dataset, and the optimal sliding pile drilling scheme is output.

[0100] In this step, based on the difference analysis results, the weights of the multilayer feedforward neural network are dynamically corrected through an online transfer learning mechanism. High-confidence samples from the validation dataset are added to the training set and mixed with the original simulation samples. The high-level response prediction layer in the multilayer feedforward neural network is locally fine-tuned. The multi-objective regression and classification joint prediction is rerun through the optimized neural network model to generate a new round of drill bit combination schemes. The optimal slip pile drilling scheme that achieves the best balance between hole quality, construction efficiency, energy consumption control and equipment wear is selected again through Pareto front screening.

[0101] Example 2:

[0102] This embodiment provides a rectangular anti-slide pile drilling device based on multi-physics coupling, the device comprising:

[0103] The acquisition module is used to acquire geological and physical information and stratigraphic structure data;

[0104] The simulation module is used to perform multiphysics coupled drilling simulation based on the geophysical information and the stratigraphic structure data to obtain a drilling-geometry coupled model.

[0105] To clarify the specific methods for obtaining the simulation module, the following are included:

[0106] The first construction unit is used to construct a numerical geometric model based on the target site geometry in the geophysical information and the stratigraphic influence range in the stratigraphic structure data.

[0107] To clarify the specific method for obtaining the first building block, the following are included:

[0108] Boundary sub-units are used to determine spatial boundaries based on the target site geometry in the geophysical information and the stratigraphic influence range in the stratigraphic structure data, and generate a three-dimensional coupled model.

[0109] Sub-units are used to discretize the three-dimensional coupled model according to the geometric dimensions of the target site, thereby obtaining a numerical grid structure;

[0110] The constraint sub-unit is used to apply asymmetric constraint boundaries to the numerical grid structure according to the actual geostress field and the preset stratigraphic boundary conditions to obtain a numerical geometric model.

[0111] The partitioning unit is used to determine the borehole area based on the numerical geometric model. By assigning material property values ​​and partitioning the borehole area with regional parameters, a geomechanical model is obtained.

[0112] The second construction unit is used to construct, based on the drilling rig structural features and drilling rig size parameters in the geophysical information, to obtain the drill bit geometric model;

[0113] The coupling unit is used to perform spatial matching and contact interface coupling based on the numerical geometric model, the geomechanical model and the drill bit geometric model to establish a drilling-geometry coupling model.

[0114] The simulation module is used to apply control parameters to the drilling-geological coupling model, combine the drill bit parameters to perform dynamic drilling simulation, and generate a multidimensional dataset.

[0115] To clarify the specific methods for obtaining the simulation module, the following are provided:

[0116] The acquisition unit is used to acquire drilling rig parameters;

[0117] The modeling unit is used to apply drilling control parameters to the drilling-geology coupling model, and to perform group modeling based on drill bit type and formation characteristics to obtain grouped drilling rig models;

[0118] The assignment unit is used to assign real construction parameters to the drill bit based on the drilling rig parameters and the grouped drilling rig model, and to perform time-domain discretization by a preset fixed time step to obtain the drill bit motion trajectory.

[0119] The calculation unit is used to calculate the contact area between the drill bit and the formation in real time based on the drill bit's movement trajectory, and to obtain the drilling space distribution by updating the contact boundary conditions.

[0120] The monitoring unit is used to monitor the stress distribution on the drill bit surface hourly based on the drill bit motion parameters and preset contact states in the drilling rig parameters, and output monitoring data.

[0121] An integration unit is used to integrate the drill bit movement trajectory, the drilling spatial distribution, and the monitoring data to generate a multidimensional dataset.

[0122] The prediction module is used to perform mixed training of simulation and measured samples on the multidimensional dataset, and to predict the scheme through a multi-layer feedforward neural network to obtain an optimized drilling scheme.

[0123] To clarify the specific methods for obtaining the prediction module, the following are included:

[0124] The preprocessing unit is used to preprocess the simulated samples and measured samples in the multidimensional dataset to obtain the training feature set;

[0125] The training unit is used to jointly train and construct an initial neural network model based on the training feature set and the multi-layer feedforward neural network, combined with simulation and measured data in the training feature set.

[0126] The first prediction unit is used to input the real-time geological parameters of the target stratum into the initial neural network model to predict the response results under different combinations of drilling parameters, and to perform multi-objective optimization by combining a genetic algorithm to obtain candidate drilling schemes.

[0127] The update unit is used to dynamically update and self-learn the initial neural network model based on the feedback learning mechanism to obtain an optimized neural network model.

[0128] The second prediction unit is used to input the candidate drilling scheme into the optimized neural network model to predict the drilling response and obtain the optimized drilling scheme.

[0129] The construction module is used to verify and construct the anti-slide pile hole formation based on the optimized drilling scheme, so as to obtain the optimal anti-slide pile hole formation scheme.

[0130] It should be noted that the specific manner in which each module performs its operation in the apparatus described in the above embodiments has been described in detail in the embodiments of the method, and will not be elaborated here.

[0131] Example 3:

[0132] Corresponding to the above method embodiments, this embodiment also provides a rectangular anti-slide pile drilling device based on multi-physics field coupling. The rectangular anti-slide pile drilling device based on multi-physics field coupling described below and the rectangular anti-slide pile drilling method based on multi-physics field coupling described above can be referred to in correspondence.

[0133] Figure 5 This is a block diagram illustrating a rectangular anti-slide pile drilling device 800 based on multiphysics coupling, according to an exemplary embodiment. Figure 5 As shown, the rectangular anti-slide pile drilling device 800 based on multiphysics coupling may include: a processor 801 and a memory 802. The rectangular anti-slide pile drilling device 800 based on multiphysics coupling may also include one or more of the following: a multimedia component 803, an I / O interface 804, and a communication component 805.

[0134] The processor 801 controls the overall operation of the rectangular anti-slide pile drilling device 800 based on multiphysics coupling to complete all or part of the steps in the aforementioned rectangular anti-slide pile drilling method based on multiphysics coupling. The memory 802 stores various types of data to support the operation of the rectangular anti-slide pile drilling device 800. This data may include, for example, instructions for any application or method operating on the rectangular anti-slide pile drilling device 800, as well as application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 802 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 805 is used for wired or wireless communication between the rectangular anti-slip pile drilling device 800 based on multi-physics coupling and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0135] In an exemplary embodiment, the rectangular anti-slide pile drilling device 800 based on multi-physics coupling can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described rectangular anti-slide pile drilling method based on multi-physics coupling.

[0136] Example 4:

[0137] Corresponding to the above method embodiments, this embodiment also provides a medium. The medium described below can be referred to in relation to the rectangular anti-slide pile drilling method based on multi-physics coupling described above.

[0138] A medium storing a computer program, which, when executed by a processor, implements the steps of the rectangular anti-slide pile drilling method based on multiphysics coupling described in the above method embodiments.

[0139] The medium can specifically be any medium capable of storing program code, such as a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0140] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0141] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for drilling rectangular anti-slide piles based on multiphysics coupling, characterized in that, include: To acquire geophysical information and stratigraphic data; Based on the geophysical information and the stratigraphic structure data, a multiphysics field coupled drilling simulation is performed to obtain a drilling-geometry coupled model. Control parameters are applied to the drilling-geology coupling model, and dynamic drilling simulation is performed in combination with drill bit parameters to generate a multidimensional dataset. The multidimensional dataset is trained using a combination of simulation and experimental samples. A multi-layer feedforward neural network is then used to predict the drilling scheme, resulting in an optimized drilling scheme. Based on the optimized drilling scheme, the anti-slide pile hole formation was verified and constructed to obtain the optimal anti-slide pile hole formation scheme.

2. The method for forming rectangular anti-slide piles based on multi-physics coupling according to claim 1, characterized in that, Based on the aforementioned geophysical information and formation structure data, a multiphysics coupled drilling simulation is performed to obtain a drilling-geological coupled model, including: A numerical geometric model is constructed based on the target site geometry in the geophysical information and the stratigraphic influence range in the stratigraphic structure data. Based on the numerical geometric model, the borehole area is determined, and a geomechanical model is obtained by assigning material properties and dividing the borehole area into regional parameters. A geometric model of the drill bit is constructed based on the structural features and size parameters of the drilling rig in the geophysical information. Based on the numerical geometric model, the geomechanical model, and the drill bit geometric model, spatial matching and contact interface coupling are performed to establish a drilling-geometry coupling model.

3. The method for forming a rectangular anti-slide pile based on multi-physics coupling according to claim 2, characterized in that, A numerical geometric model is constructed based on the target site geometry in the geophysical information and the stratigraphic influence range in the stratigraphic structure data, including: Based on the target site geometry in the geophysical information and the stratigraphic influence range in the stratigraphic structure data, the spatial boundary is determined and a three-dimensional coupled model is generated. The three-dimensional coupled model is discretized according to the geometric dimensions of the target site to obtain a numerical mesh structure; Asymmetric constraint boundaries are applied to the numerical grid structure based on the actual geostress field and the preset stratigraphic boundary conditions to obtain a numerical geometric model.

4. The method for forming a rectangular anti-slide pile based on multi-physics coupling according to claim 1, characterized in that, Control parameters are applied to the drilling-geological coupling model, and dynamic drilling simulation is performed in conjunction with drill bit parameters to generate a multidimensional dataset, including: Obtain drilling rig parameters; Drilling control parameters are applied to the drilling-geology coupling model, and grouping models are performed based on drill bit type and formation characteristics to obtain grouped drilling rig models; Based on the drilling rig parameters and the grouped drilling rig model, the drill bit is assigned real construction parameters, and time-domain discretization is performed by a preset fixed time step to obtain the drill bit motion trajectory. The contact area between the drill bit and the formation is calculated in real time based on the drill bit's movement trajectory. By updating the contact boundary conditions, the drilling space distribution is obtained. Based on the drill bit motion parameters and preset contact states in the drilling rig parameters, the stress distribution on the drill bit surface is monitored hourly, and monitoring data is output. A multidimensional dataset is generated by integrating the drill bit's movement trajectory, the spatial distribution of the drilling site, and the monitoring data.

5. The method for forming rectangular anti-slide piles based on multi-physics coupling according to claim 1, characterized in that, The multidimensional dataset is trained using a mixture of simulation and experimental samples. A multi-layer feedforward neural network is then used to predict the optimal drilling scheme, which includes: The simulated samples and measured samples in the multidimensional dataset are preprocessed to obtain a training feature set; Based on the training feature set and the multi-layer feedforward neural network, an initial neural network model is obtained by jointly training and constructing the simulation and measured data in the training feature set. The real-time geological parameters of the target stratum are input into the initial neural network model to predict the response results under different combinations of drilling parameters. Multi-objective optimization is performed by combining a genetic algorithm to obtain candidate drilling schemes. The initial neural network model is dynamically updated and self-learned based on a feedback learning mechanism to obtain an optimized neural network model. The candidate drilling schemes are input into the optimized neural network model to predict the drilling response, thereby obtaining the optimized drilling scheme.

6. A rectangular anti-slide pile drilling device based on multiphysics coupling, characterized in that, include: The acquisition module is used to acquire geological and physical information and stratigraphic structure data; The simulation module is used to perform multiphysics coupled drilling simulation based on the geophysical information and the stratigraphic structure data to obtain a drilling-geometry coupled model. The simulation module is used to apply control parameters to the drilling-geological coupling model, combine the drill bit parameters to perform dynamic drilling simulation, and generate a multidimensional dataset. The prediction module is used to perform mixed training of simulation and measured samples on the multidimensional dataset, and to predict the scheme through a multi-layer feedforward neural network to obtain an optimized drilling scheme. The construction module is used to verify and construct the anti-slide pile hole formation based on the optimized drilling scheme, so as to obtain the optimal anti-slide pile hole formation scheme.

7. The rectangular anti-slide pile drilling device based on multiphysics coupling according to claim 6, characterized in that, The simulation module includes: The first construction unit is used to construct a numerical geometric model based on the target site geometry in the geophysical information and the stratigraphic influence range in the stratigraphic structure data. The partitioning unit is used to determine the borehole area based on the numerical geometric model. By assigning material property values ​​and partitioning the borehole area with regional parameters, a geomechanical model is obtained. The second construction unit is used to construct, based on the drilling rig structural features and drilling rig size parameters in the geophysical information, to obtain the drill bit geometric model; The coupling unit is used to perform spatial matching and contact interface coupling based on the numerical geometric model, the geomechanical model and the drill bit geometric model to establish a drilling-geometry coupling model.

8. The rectangular anti-slide pile drilling device based on multiphysics coupling according to claim 7, characterized in that, The first building unit includes: Boundary sub-units are used to determine spatial boundaries based on the target site geometry in the geophysical information and the stratigraphic influence range in the stratigraphic structure data, and generate a three-dimensional coupled model. Sub-units are used to discretize the three-dimensional coupled model according to the geometric dimensions of the target site, thereby obtaining a numerical grid structure; The constraint sub-unit is used to apply asymmetric constraint boundaries to the numerical grid structure according to the actual geostress field and the preset stratigraphic boundary conditions to obtain a numerical geometric model.

9. The rectangular anti-slide pile drilling device based on multiphysics coupling according to claim 6, characterized in that, The simulation module includes: The acquisition unit is used to acquire drilling rig parameters; The modeling unit is used to apply drilling control parameters to the drilling-geology coupling model, and to perform group modeling based on drill bit type and formation characteristics to obtain grouped drilling rig models; The assignment unit is used to assign real construction parameters to the drill bit based on the drilling rig parameters and the grouped drilling rig model, and to perform time-domain discretization by a preset fixed time step to obtain the drill bit motion trajectory. The calculation unit is used to calculate the contact area between the drill bit and the formation in real time based on the drill bit's movement trajectory, and to obtain the drilling space distribution by updating the contact boundary conditions. The monitoring unit is used to monitor the stress distribution on the drill bit surface hourly based on the drill bit motion parameters and preset contact states in the drilling rig parameters, and output monitoring data. An integration unit is used to integrate the drill bit movement trajectory, the drilling spatial distribution, and the monitoring data to generate a multidimensional dataset.

10. The rectangular anti-slide pile drilling device based on multi-physics coupling according to claim 6, characterized in that, The multidimensional dataset is trained using a mixture of simulation and experimental samples. A multi-layer feedforward neural network is then used to predict the optimal drilling scheme, which includes: The preprocessing unit is used to preprocess the simulated samples and measured samples in the multidimensional dataset to obtain the training feature set; The training unit is used to jointly train and construct an initial neural network model based on the training feature set and the multi-layer feedforward neural network, combined with simulation and measured data in the training feature set. The first prediction unit is used to input the real-time geological parameters of the target stratum into the initial neural network model to predict the response results under different combinations of drilling parameters, and to perform multi-objective optimization by combining a genetic algorithm to obtain candidate drilling schemes. The update unit is used to dynamically update and self-learn the initial neural network model based on the feedback learning mechanism to obtain an optimized neural network model. The second prediction unit is used to input the candidate drilling scheme into the optimized neural network model to predict the drilling response and obtain the optimized drilling scheme.

Images