A pile foundation construction pile forming verticality control method and system
By using a multilayer perceptron network and adaptive PID control, the problem of insufficient prediction of stratum changes in traditional verticality control technology has been solved, achieving precise control of the verticality of the support piles and improving construction efficiency and safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GUANGDONG NO 2 HYDROPOWER ENGINEERING COMPANY LTD
- Filing Date
- 2026-04-16
- Publication Date
- 2026-07-14
AI Technical Summary
Traditional verticality control technology cannot effectively predict changes in the strata, leading to the accumulation of verticality deviations during the construction of the bearing piles, resulting in project delays and increased costs. Furthermore, the lack of accurate prediction of the location of the stratum interface leads to a lag in correction.
A GeoINR continuous stratigraphic model is constructed using a multilayer perceptron network. Stratigraphic information is predicted by training with basic exploration data. Combined with adaptive PID control, the verticality control parameters are adjusted in real time to achieve decoupled control of stratigraphic anisotropy.
It has achieved a systematic upgrade in the verticality of the bearing piles, predicted and actively intervened in stratum changes, prevented abrupt changes in verticality, improved construction efficiency and accuracy, and reduced construction risks.
Smart Images
Figure CN122386619A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of pile foundation construction technology, specifically relating to a method and system for controlling the verticality of pile foundation support piles. Background Technology
[0002] Verticality control of the bearing capacity of the pile foundation is a crucial factor determining the success or failure of construction. Traditional verticality control techniques mainly rely on two methods: process monitoring and dynamic correction. Deviation in any of these methods can prevent the expansion equipment from being lowered to the intended position, or cause the bearing foundation to be misaligned or subjected to uneven stress. In severe cases, it can even lead to accidents such as stuck drill bits or hole collapse.
[0003] The construction of pile foundations involves two key processes: main pile drilling and foundation expansion. The verticality of these foundations is significantly affected by geological characteristics. In current construction processes, obtaining geological information mainly relies on core analysis after drilling and pressure feedback during the expansion process. While dynamic tracking of geological changes is required during each pile drilling operation, this approach is reactive and often results in verticality deviations accumulating to the point of requiring correction (such as backfilling and re-drilling), leading to project delays and increased costs. Furthermore, traditional methods lack a quantitative correlation between geological parameters and drilling process parameters, making it impossible to predict verticality risks and optimize drilling strategies based on prior geological information. Summary of the Invention
[0004] The purpose of this invention is to provide a method and system for controlling the verticality of pile foundation support piles during construction, in order to improve the aforementioned problems. To achieve the above objective, the technical solution adopted by this invention is as follows:
[0005] Firstly, this application provides a method for controlling the verticality of the forming of pile foundation support piles, including:
[0006] Acquire basic exploration data, which includes stratigraphic data from boreholes at different locations in the construction area;
[0007] The construction area is divided into several subspaces, and a multilayer perceptron network is constructed. Each neuron in the first hidden layer of the multilayer perceptron network is assigned a unique associated subspace.
[0008] A signed distance field is constructed based on the formation data from the boreholes; the signed distance of each subspace is calculated based on the signed distance field.
[0009] The initial weights of the first hidden layer neurons are determined based on the signed distance of the subspaces associated with the neurons, and the multilayer perceptron network is initialized accordingly.
[0010] The initial multilayer perceptron network was trained using basic exploration data to learn the continuous mapping from spatial coordinates to stratigraphic attributes, thus obtaining a prediction model.
[0011] The coordinates of each pile to be constructed are input into the prediction model to obtain the geological information of the location to be constructed, including the geological anisotropy.
[0012] During construction, acquire construction monitoring data and calculate verticality deviation;
[0013] Adjust the verticality control parameters based on predicted stratigraphic information and verticality deviation.
[0014] Secondly, this application also provides a verticality control system for the forming of pile foundation support piles, characterized in that it includes:
[0015] The first module is used to acquire basic exploration data, which includes stratigraphic data from boreholes at different locations in the construction area.
[0016] The second module is used to divide the construction area into several subspaces, construct a multilayer perceptron network, and assign a unique associated subspace to each neuron in the first hidden layer of the multilayer perceptron network.
[0017] The third module is used to construct a signed distance field based on the formation data from the borehole; and to calculate the signed distance of each subspace based on the signed distance field.
[0018] The fourth module is used to determine the initial weights of the first hidden layer neurons based on the signed distance of the subspaces associated with the neurons, and to initialize the multilayer perceptron network.
[0019] The fifth module is used to train the initialized multilayer perceptron network using basic exploration data, learn the continuous mapping from spatial coordinates to stratigraphic attributes, and obtain the prediction model.
[0020] The sixth module is used to input the coordinates of each pile to be constructed into the prediction model to obtain the stratum information of the location to be constructed, including the stratum anisotropy.
[0021] The seventh module is used to acquire construction monitoring data and calculate verticality deviation during the construction process;
[0022] The eighth module is used to adjust the verticality control parameters based on the predicted stratigraphic information and verticality deviation.
[0023] The beneficial effects of this invention are as follows:
[0024] This method constructs a GeoINR continuous formation model to predict the formation attitude of the drilling borehole and converts it into anisotropic tensors, achieving decoupled control in the X / Y directions. It utilizes interface prediction information to adjust parameters in advance, proactively intervening before deviations occur to effectively prevent abrupt changes in verticality. Adaptive PID control based on formation conditions represents a systematic upgrade to the verticality control of the pile supports.
[0025] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. Attached Figure Description
[0026] 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.
[0027] Figure 1 This is a flowchart illustrating the method for controlling the verticality of pile foundation construction support piles according to an embodiment of this application.
[0028] Figure 2 This is a structural diagram of the verticality control device for pile foundation construction support pile forming in an embodiment of this application.
[0029] Symbol explanation: 800 - Verticality control equipment for pile foundation construction support pile forming; 801 - Processor; 802 - Memory; 803 - Multimedia component; 804 - I / O interface; 805 - Communication component. Detailed Implementation
[0030] 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.
[0031] It should be noted that similar labels 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.
[0032] In areas with large dip angles of sedimentary strata, significant anisotropy, large undulations of stratigraphic interfaces, or faults and fracture zones, pile foundation construction is quite difficult, especially for important projects with strict requirements for pile verticality (such as bridges and super high-rise buildings).
[0033] Current exploration boreholes can only provide discrete points of geological information, failing to reveal continuous spatial variations in the strata. When the pile location deviates from the borehole position, construction personnel can only infer the geological conditions based on experience, leading to a lack of basis for setting construction parameters. In inclined strata, the mechanical properties of the strata differ in different horizontal directions, and the pile body will be subjected to lateral thrust pointing in the downward dip direction of the strata during pile driving. Traditional methods cannot quantify this anisotropy, relying solely on operator intuition for correction, resulting in inconsistent effectiveness. When the pile body moves from a soft layer to a hard layer or vice versa, the stress state changes drastically, and verticality can easily abruptly change at the interface. Traditional methods lack precise prediction of the interface position, often only initiating correction after deviation has occurred, exhibiting a lag.
[0034] Example 1:
[0035] See Figure 1 To address the problems existing in the prior art, this application provides a method for controlling the verticality of the forming of the pile foundation support pile, characterized by comprising the following steps: S100, S200, S300, S400, S500, S600, S700, and S800.
[0036] S100. Obtain basic exploration data, which includes stratigraphic data from boreholes at different locations in the construction area;
[0037] Drilling is carried out in advance within the construction area. Preferably, the drilling points cover the construction area relatively evenly to ensure the accuracy of model fitting.
[0038] S110. Construct a basic three-dimensional coordinate system for the construction area and determine the coordinates of each existing borehole (perpendicular to the ground); conduct a preliminary survey of each borehole.
[0039] S120. Obtain the lithological characteristics of the formation in the vertical direction of each borehole, identify the stratigraphic interfaces based on the lithological characteristics, and determine the coordinates of the stratigraphic interfaces.
[0040] The lithological characteristics of the strata include parameters such as soil and rock type and hardness, which can be obtained directly through core sampling analysis.
[0041] The strata are stratified according to their type, including but not limited to clay layers, sand layers, weathered rocks, etc.; at the same time, the interface locations between different types of strata are determined; in this step, the coordinate system space can be discretized into a grid space according to the minimum exploration scale to obtain discrete basic exploration data.
[0042] S130. Based on the geological map of the construction area, the stratigraphic interface of adjacent boreholes, and the construction offset data, the vertical stratigraphic attitude of the boreholes is inverted.
[0043] Stratigraphic attitude refers to the spatial distribution of rock strata or geological interfaces, which is determined by three basic elements: strike, dip, and dip angle.
[0044] Strike direction: The direction of the intersection of the bedding plane and the horizontal plane, representing the horizontal extension direction of the rock strata in space;
[0045] Dip: The direction of the projection of a straight line (dip line) perpendicular to the strike line and downward along the dip surface onto the horizontal plane.
[0046] Inclination angle: The angle between the inclined line and its projection line on the horizontal plane, that is, the maximum angle between the plane and the horizontal plane;
[0047] Based on the above stratigraphic attitude, the anisotropic characteristics of the internal structural planes of the rock and soil mass can be analyzed. The stratigraphic attitude is transformed into anisotropic tensors. This method mainly focuses on the anisotropy in the horizontal plane (because the verticality deviation mainly occurs in the horizontal direction), so it can be simplified to a 2×2 tensor.
[0048] Specifically, a local coordinate system is constructed based on the formation normal vector, strike vector, and dip direction vector. In this local coordinate system, the stiffness or strength of the formation exhibits intrinsic differences in different directions, which can be represented by three eigenvalues:
[0049] Eigenvalues of direction Set the baseline value to 1.0. The orientation is parallel to the floor plan and horizontal, with the weakest inter-story constraint, resulting in the lowest stiffness.
[0050] Eigenvalues in the direction of inclination An increment related to the dip angle is added to the baseline value. The larger the dip angle, the more significant the gravity compaction effect, and the higher the stiffness in the dip direction. The increment coefficient is usually between 0.2 and 0.5, adjusted according to the lithology of the strata and the burial depth.
[0051] Eigenvalues in the normal direction A larger increment is added to the baseline value. The normal direction is perpendicular to the bedding plane and needs to cross the bedding interface, thus having the highest stiffness. The increment factor is typically between 0.5 and 1.0.
[0052] These three eigenvalues form a diagonal matrix, called the eigenanisotropy tensor in the local coordinate system. This tensor expresses the relative stiffness in three orthogonal directions in the local coordinate system:
[0053]
[0054] in, It is a diagonal matrix. The eigenvalues representing the direction of travel. The eigenvalues are the eigenvalues in the direction of inclination. The eigenvalues are those in the normal direction;
[0055] Rotate the anisotropic tensor in the local coordinate system to the base coordinate system (using east, north, and vertical as the three axes) to obtain the anisotropic tensor in the global coordinate system.
[0056] Using the basis vectors of the local coordinate system as column vectors, we construct a rotation matrix R. Then, we perform transformations based on rotation matrix R to obtain the anisotropic tensor in the global coordinate system.
[0057]
[0058] in, This is an anisotropic tensor in the global coordinate system, containing nine components. The diagonal component... , , Represents the stiffness coefficients in the east, north, and vertical directions, with off-diagonal components. , , , , , This represents the coupling effect (coupling stiffness coefficient) between different directions.
[0059] Since pile verticality control mainly focuses on the horizontal offset of the pile, it is necessary to extract the horizontal portion from the three-dimensional tensor to obtain a 2×2 matrix:
[0060]
[0061] in, Let be the horizontal plane tensor, where the diagonal components are... , Indicates the stiffness coefficients in the east and north directions. , This represents the coupling effect (coupling stiffness coefficient) between different directions.
[0062] Calculate the eigenvalues and eigenvectors of the horizontal plane tensor. The direction of the eigenvector corresponding to the smallest eigenvalue is the direction of lowest soil stiffness, which is also the direction in which the pile is most likely to deviate. The direction of the eigenvector corresponding to the largest eigenvalue is the direction of highest soil stiffness.
[0063] S200. Divide the construction area into several subspaces, construct a multilayer perceptron network, and assign a unique associated subspace to each neuron in the first hidden layer of the multilayer perceptron network.
[0064] This application adopts the GeoINR model framework, which is a pure multilayer perceptron structure. The input layer includes three neurons, receiving X, Y, and Z coordinates respectively. The hidden layers typically consist of 6 to 8 layers, each containing 256 neurons, and all layers are fully connected. The output dimension of the output layer is determined according to the modeling requirements; this application requires at least the output of formation type, hardness value, and anisotropy, therefore it includes at least three output branches.
[0065] The model employs a sinusoidal activation function, a periodic activation function that enables the network to better represent abrupt changes at geological interfaces while maintaining smooth variations within continuous intervals.
[0066] Traditional random initialization requires a large amount of data for the network to learn the location of stratigraphic interfaces. To accelerate learning, this application performs geometric initialization on the network, using known geological knowledge to assign it a reasonable initial state before training begins. Therefore, the area to be constructed is first divided into several subspaces, and each neuron in the first hidden layer is assigned to be responsible for one subspace.
[0067] S300. Construct a signed distance field based on the formation data from the borehole; calculate the signed distance of each subspace based on the signed distance field;
[0068] S310. Delineate formation interfaces based on borehole formation data;
[0069] S320. For any point in the borehole, calculate the distance from that point to the nearest formation interface;
[0070] S330. Determine whether the point is located above the nearest stratigraphic interface. If so, assign a positive sign to the distance; otherwise, assign a negative sign to the distance, thus obtaining the signed distance of any point.
[0071] S400. Determine the initial weights of the first hidden layer neurons based on the signed distance of the subspaces associated with the neurons, and perform multilayer perceptron network initialization.
[0072] The core of geometric initialization is to align the initial output of the network with the signed distance field. Each neuron is regarded as a "representative" of a certain position in space, and its weight is initialized as a function of the position coordinates represented by the neuron. The output of shallow neurons is approximately equal to the distance function between the input coordinates and the coordinates represented by the neuron. Deep neurons can express more complex interface combinations by combining the outputs of shallow neurons, thus making the entire network a spatially adaptive function representation.
[0073] Before training begins, the network already has the ability to "know roughly where the stratigraphic interface is". Subsequent training only requires fine-tuning the interface position with data, which greatly reduces the data requirements.
[0074] S500: The initial multilayer perceptron network is trained using basic exploration data to learn the continuous mapping from spatial coordinates to stratigraphic attributes, and a prediction model is obtained.
[0075] The basic survey data was divided into training and testing sets to train the multilayer perceptron network; the loss function of the model was designed as follows:
[0076] A data fitting loss term is constructed based on the differences between the model-predicted stratification interface, lithological characteristics, and actual data.
[0077] The specific steps involved in constructing the data fitting loss term include:
[0078] The interface point fitting loss is calculated based on the difference between the interface value predicted by the model and the actual interface value; the lithology fitting loss is calculated based on the difference between the lithological characteristics predicted by the model and the actual lithological characteristics; for points with known stratigraphic attitudes, the gradient direction of the model at that point should be consistent with the stratigraphic normal direction, so the cosine deviation of the angle between the gradient direction and the actual normal direction is calculated to obtain the direction point fitting loss.
[0079] For all vertically adjacent point pairs, a stratigraphic overlay constraint loss term is constructed by detecting whether the stratigraphic age of the upper point is greater than that of the lower stratigraphic age. That is, at the same vertical position, the chronological order of the strata is from youngest to oldest from top to bottom. When the age value of the upper unit is greater than that of the lower unit, a penalty is generated. In this way, the stratigraphic sequence output by the model is forced to conform to geological logic.
[0080] Although there are abrupt interfaces in the geological structure, the properties should change smoothly within the same geological unit. Therefore, in non-layered interface regions, the gradient value of the model prediction results with respect to spatial coordinates is calculated, and a smoothness constraint loss term is constructed based on the gradient value. Near the layered interface, this constraint is automatically relaxed, allowing abrupt gradient changes.
[0081] The loss function of the prediction model is constructed based on the data fitting loss term, the formation stacking constraint loss term, and the smoothness constraint loss term.
[0082] S600. Input the coordinates of each pile to be constructed into the prediction model to obtain the stratum information of the location to be constructed. The stratum information includes stratum anisotropy (horizontal plane tensor).
[0083] The predictive model learns the geological distribution function across the entire three-dimensional space. For any input coordinate point, the model outputs the geological properties at that point. Therefore, based on this model, the geological conditions of any unconstructed pile location can be queried at any time. Before construction, the pile location can be dynamically adjusted according to actual construction needs, and the impact of design changes (such as pile length adjustments) can be quickly assessed.
[0084] S700: Acquire construction monitoring data during construction and calculate verticality deviation;
[0085] Specifically, a dual-axis tilt sensor is used to monitor the tilt angle of the pile in real time, and a depth sensor is used to record the current construction depth. The depth is then converted into the coordinates of the bottom of the pile in the foundation coordinate system and correlated with the deviation data.
[0086] The deviation in different directions is calculated based on the inclination angle of the pile.
[0087] S800: Adjust the verticality control parameters based on the predicted stratigraphic information and verticality deviation;
[0088] S810. When the distance between the pile and the anisotropic stratum reaches the preset value, calculate the reverse compensation angle based on the anisotropy of the stratum; adjust the pile platform angle in advance based on the reverse compensation angle.
[0089] For example, 0.5 meters before reaching the anisotropic stratum, the hydraulic outriggers are adjusted to tilt the pile driver platform in the opposite direction of the predicted offset. When the pile enters the anisotropic stratum interface, the initial attitude has already offset part of the stratum thrust, effectively reducing the degree of verticality deviation.
[0090] S820. Obtain the verticality deviation of the pile and calculate the rate of change of the deviation.
[0091] S830. Based on the verticality deviation and the rate of change of the deviation, the verticality control parameters are adjusted by a variable parameter adaptive PID; wherein, the PID parameters are dynamically adjusted according to the predicted lithological characteristics and anisotropy of the formation.
[0092] During the interface transition phase, the proportional gain is increased, the integral gain is decreased, and the derivative gain is increased (for faster response). The horizontal anisotropic tensor is directly used for differentiated configuration of PID gain in the X and Y directions: the control gain is adjusted in reverse according to the ratio of stiffness coefficients in the two directions; in the direction with lower stiffness, the proportional gain needs to be reduced to prevent overcorrection because the formation responds to correction faster; in the direction with higher stiffness, the proportional gain needs to be increased to ensure correction capability because the formation responds to correction slower.
[0093] Optionally, when the display is about to reach the interface for changing between soft and hard parameters, the mode can be adjusted to light pressure and slow rotation at the interface to prevent the drill bit from deviating. After passing through the interface, the normal parameters can be gradually restored.
[0094] The above methods can control verticality deviation within the allowable range and improve construction efficiency.
[0095] For existing piles, the drilling parameters during the construction process are obtained, and the lithological characteristics of the strata are inverted based on the drilling parameters; the drilling parameters include drilling speed, drilling pressure torque and drilling current;
[0096] Obtain verticality offset information during construction and invert the anisotropy of the strata based on the verticality offset information;
[0097] The inverted stratigraphic lithology and stratigraphic anisotropy of the constructed piles are used as training samples and input into the prediction model for incremental updates.
[0098] The prediction of subsequent pile locations benefits from the construction data of all previous piles, and the model predictions become more and more accurate, forming a positive cycle.
[0099] Example 2:
[0100] A verticality control system for pile foundation construction support piles includes:
[0101] The first module is used to acquire basic exploration data, which includes stratigraphic data from boreholes at different locations in the construction area.
[0102] The second module is used to divide the construction area into several subspaces, construct a multilayer perceptron network, and assign a unique associated subspace to each neuron in the first hidden layer of the multilayer perceptron network.
[0103] The third module is used to construct a signed distance field based on the formation data from the borehole; and to calculate the signed distance of each subspace based on the signed distance field.
[0104] The fourth module is used to determine the initial weights of the first hidden layer neurons based on the signed distance of the subspaces associated with the neurons, and to initialize the multilayer perceptron network.
[0105] The fifth module is used to train the initialized multilayer perceptron network using basic exploration data, learn the continuous mapping from spatial coordinates to stratigraphic attributes, and obtain the prediction model.
[0106] The sixth module is used to input the coordinates of each pile to be constructed into the prediction model to obtain the stratum information of the location to be constructed, including the stratum anisotropy.
[0107] The seventh module is used to acquire construction monitoring data and calculate verticality deviation during the construction process;
[0108] The eighth module is used to adjust the verticality control parameters based on the predicted stratigraphic information and verticality deviation.
[0109] As an optional implementation, the first module includes:
[0110] The first unit is used to construct a basic three-dimensional coordinate system for the construction area and determine the coordinates of each existing borehole;
[0111] The second unit is used to obtain the lithological characteristics of the formation in the vertical direction of each borehole, identify the stratigraphic interfaces based on the lithological characteristics, and determine the coordinates of the stratigraphic interfaces.
[0112] The third unit is used to invert the vertical stratigraphic attitude of the boreholes based on the geological map of the construction area, the stratigraphic interface of adjacent boreholes, and construction offset data.
[0113] As an optional implementation, the third module includes:
[0114] The fourth unit is used to delineate formation interfaces based on borehole formation data;
[0115] The fifth unit is used to calculate the distance from any point in the borehole to the nearest formation interface.
[0116] The sixth unit is used to determine whether the point is located above the nearest stratigraphic interface. If it is, the distance is assigned a positive sign; otherwise, the distance is assigned a negative sign, thus obtaining the signed distance of any point.
[0117] As an optional implementation, the system further includes:
[0118] The ninth module is used to obtain drilling parameters during the construction process of the constructed piles and to invert the lithological characteristics of the strata based on the drilling parameters; the drilling parameters include drilling speed, drilling pressure torque and drilling current;
[0119] The tenth module is used to obtain verticality offset information during construction and to invert the anisotropy of the strata based on the verticality offset information.
[0120] The eleventh module is used to take the inverted lithological characteristics and anisotropy of the constructed piles as training samples and input them into the prediction model for incremental updates.
[0121] Example 3:
[0122] Corresponding to the above method embodiments, this embodiment also provides a verticality control device for pile foundation construction support pile forming. The verticality control device for pile foundation construction support pile forming described below can be referred to in correspondence with the verticality control method for pile foundation construction support pile forming described above.
[0123] Figure 2 This is a block diagram illustrating a verticality control device 800 for pile foundation construction support pile forming, according to an exemplary embodiment. Figure 2As shown, the pile foundation construction support pile forming verticality control device 800 includes a processor 801 and a memory 802. The pile foundation construction support pile forming verticality control device 800 may also include one or more of the following: a multimedia component 803, an input / output (I / O) interface 804, and a communication component 805. The processor 801 controls the overall operation of the pile foundation construction support pile forming verticality control device 800 to complete all or part of the steps in the aforementioned pile foundation construction support pile forming verticality control method. The memory 802 stores various types of data to support the operation of the pile foundation construction support pile forming verticality control device 800. This data may include, for example, commands for any application or method operating on the pile foundation construction support pile forming verticality control device 800, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by 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.
[0124] 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.
[0125] The received audio signal can be further stored in memory 802 or transmitted via 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 a keyboard, mouse, buttons, etc. These buttons can be virtual or physical buttons. Communication component 805 is used for wired or wireless communication between the pile foundation construction support pile forming verticality control device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof, is used. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, or an NFC module.
[0126] Example 4:
[0127] Corresponding to the above embodiment of the method for controlling the verticality of pile foundation construction support piles, this embodiment also provides a readable storage medium. The readable storage medium described below can be referred to in correspondence with the above-described method for controlling the verticality of pile foundation construction support piles.
[0128] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described embodiment of the method for controlling the verticality of pile foundation construction support piles.
[0129] Specifically, the readable storage medium can be a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or any other readable storage medium capable of storing program code.
[0130] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0131] 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 controlling the verticality of pile foundation support piles during construction, characterized in that, include: Acquire basic exploration data, which includes stratigraphic data from boreholes at different locations in the construction area; The construction area is divided into several subspaces, and a multilayer perceptron network is constructed. Each neuron in the first hidden layer of the multilayer perceptron network is assigned a unique associated subspace. A signed distance field is constructed based on the formation data from the boreholes; the signed distance of each subspace is calculated based on the signed distance field. The initial weights of the first hidden layer neurons are determined based on the signed distance of the subspaces associated with the neurons, and the multilayer perceptron network is initialized accordingly. The initial multilayer perceptron network was trained using basic exploration data to learn the continuous mapping from spatial coordinates to stratigraphic attributes, thus obtaining a prediction model. The coordinates of each pile to be constructed are input into the prediction model to obtain the geological information of the location to be constructed, including the geological anisotropy. During construction, acquire construction monitoring data and calculate verticality deviation; Adjust the verticality control parameters based on predicted stratigraphic information and verticality deviation.
2. The method for controlling the verticality of pile foundation support piles according to claim 1, characterized in that, The acquisition of basic survey data includes: Establish a basic three-dimensional coordinate system for the construction area and determine the coordinates of each existing borehole; Obtain the lithological characteristics of the stratigraphy in the vertical direction for each borehole, identify the stratigraphic interfaces based on the lithological characteristics, and determine the coordinates of the stratigraphic interfaces. The formation attitude in the vertical direction of the boreholes was inverted based on the geological map of the construction area, the stratigraphic interface of adjacent boreholes, and the construction offset data.
3. The method for controlling the verticality of pile foundation support piles according to claim 1, characterized in that, A signed distance field was constructed based on the formation data from the boreholes, including: Formation boundaries are defined based on borehole formation data; For any point in the borehole, calculate the distance from that point to the nearest formation interface; Determine whether the point is located above the nearest stratigraphic boundary. If so, assign a positive sign to the distance; otherwise, assign a negative sign to the distance, thus obtaining the signed distance of any point.
4. The method for controlling the verticality of pile foundation support piles according to claim 1, characterized in that, The method includes: For existing piles, the drilling parameters during the construction process are obtained, and the lithological characteristics of the strata are inverted based on the drilling parameters; the drilling parameters include drilling speed, drilling pressure torque and drilling current; Obtain verticality offset information during construction and invert the anisotropy of the strata based on the verticality offset information; The inverted stratigraphic lithology and stratigraphic anisotropy of the constructed piles are used as training samples and input into the prediction model for incremental updates.
5. The method for controlling the verticality of pile foundation support piles according to claim 1, characterized in that, The method includes: A data fitting loss term is constructed based on the differences between the model-predicted stratification interface, lithological characteristics, and actual data. For all vertically adjacent point pairs, a stratigraphic stacking constraint loss term is constructed by detecting whether the stratigraphic age of the upper point is greater than that of the lower stratigraphic age. Calculate the gradient value of the model's prediction result with respect to spatial coordinates, and construct a smoothness constraint loss term based on the gradient value; The loss function of the prediction model is constructed based on the data fitting loss term, the formation stacking constraint loss term, and the smoothness constraint loss term.
6. The method for controlling the verticality of pile foundation support piles according to claim 1, characterized in that, Adjusting verticality control parameters based on predicted stratigraphic information and verticality deviation includes: When the distance between the pile and the anisotropic stratum reaches the preset value, the reverse compensation angle is calculated based on the anisotropy of the stratum; the pile platform angle is adjusted in advance based on the reverse compensation angle. Obtain the verticality deviation of the pile and calculate the rate of change of the deviation; Based on the verticality deviation and the rate of change of the deviation, a variable parameter adaptive PID is used to adjust the verticality control parameters; among which, the PID parameters are dynamically adjusted according to the predicted lithological characteristics and anisotropy of the formation.
7. A verticality control system for pile foundation construction support pile forming, characterized in that, include: The first module is used to acquire basic exploration data, which includes stratigraphic data from boreholes at different locations in the construction area. The second module is used to divide the construction area into several subspaces, construct a multilayer perceptron network, and assign a unique associated subspace to each neuron in the first hidden layer of the multilayer perceptron network. The third module is used to construct a signed distance field based on the formation data from the borehole; and to calculate the signed distance of each subspace based on the signed distance field. The fourth module is used to determine the initial weights of the first hidden layer neurons based on the signed distance of the subspaces associated with the neurons, and to initialize the multilayer perceptron network. The fifth module is used to train the initialized multilayer perceptron network using basic exploration data, learn the continuous mapping from spatial coordinates to stratigraphic attributes, and obtain the prediction model. The sixth module is used to input the coordinates of each pile to be constructed into the prediction model to obtain the stratum information of the location to be constructed, including the stratum anisotropy. The seventh module is used to acquire construction monitoring data and calculate verticality deviation during the construction process; The eighth module is used to adjust the verticality control parameters based on the predicted stratigraphic information and verticality deviation.
8. The verticality control system for pile foundation construction support pile forming according to claim 7, characterized in that, The first module includes: The first unit is used to construct a basic three-dimensional coordinate system for the construction area and determine the coordinates of each existing borehole; The second unit is used to obtain the lithological characteristics of the formation in the vertical direction of each borehole, identify the stratigraphic interfaces based on the lithological characteristics, and determine the coordinates of the stratigraphic interfaces. The third unit is used to invert the vertical stratigraphic attitude of the boreholes based on the geological map of the construction area, the stratigraphic interface of adjacent boreholes, and construction offset data.
9. A verticality control system for pile foundation construction support pile forming according to claim 7, characterized in that, The third module includes: The fourth unit is used to delineate formation interfaces based on borehole formation data; The fifth unit is used to calculate the distance from any point in the borehole to the nearest formation interface. The sixth unit is used to determine whether the point is located above the nearest stratigraphic interface. If it is, the distance is assigned a positive sign; otherwise, the distance is assigned a negative sign, thus obtaining the signed distance of any point.
10. A verticality control system for pile foundation construction support pile forming according to claim 7, characterized in that, The system also includes: The ninth module is used to obtain drilling parameters during the construction process of the constructed piles and to invert the lithological characteristics of the strata based on the drilling parameters; the drilling parameters include drilling speed, drilling pressure torque and drilling current; The tenth module is used to obtain verticality offset information during construction and to invert the anisotropy of the strata based on the verticality offset information. The eleventh module is used to take the inverted lithological characteristics and anisotropy of the constructed piles as training samples and input them into the prediction model for incremental updates.