An intelligent coupling control method for pressure-flow-deformation of spiral anchor foundation grouting

Abstract

The present invention discloses a method for intelligently coupling pressure-flow-deformation control of spiral anchor foundation grouting, which relates to the technical field of foundation grouting technology, including: matching a preset engineering parameter set according to the specification parameters of the spiral anchor and the type of soil in which it is located; collecting grouting data of each grouting channel, and calculating grouting deviation data in combination with the engineering parameter set; fuzzifying the grouting deviation data and converting it into fuzzy language variables; inputting the fuzzy language variables into a preset fuzzy rule library for reasoning, and outputting PID parameter corrections; dynamically adjusting the parameters of the PID controller according to the corrections to generate a pump speed adjustment instruction; executing the pump speed adjustment instruction and collecting the grouting data after execution; obtaining the soil permeability coefficient by inversion through the construction of a digital twin model, and optimizing and updating the fuzzy rule library in combination with the grouting data after execution. This application is used to solve the problem that the traditional spiral anchor foundation grouting process has poor adaptability to complex geology.

Description

Technical Field

[0001] The present invention relates to the technical field of foundation grouting technology, and more particularly to a method for intelligently coupling and controlling the pressure, flow rate and deformation of spiral anchor foundation grouting. Background Art

[0002] In the field of civil engineering, spiral anchors are widely used in projects such as transmission towers, photovoltaic brackets, temporary structures, and slope support due to their significant advantages such as convenient construction, high bearing capacity, and low environmental impact. Compared with traditional deep foundations, spiral anchors do not require large-scale excavation, have low construction noise and vibration, and can be installed quickly, making them particularly suitable for projects with high requirements for construction efficiency. However, under complex geological conditions, especially in soft soil layers, loose sand layers, or composite strata with uneven permeability, the bearing performance and long-term stability of traditional spiral anchors are often difficult to meet engineering requirements. Due to insufficient soil strength or low friction resistance at the anchor-soil interface, spiral anchors may suffer from problems such as insufficient bearing capacity, excessive settlement, or even overall instability, seriously affecting the safety and durability of the project.

[0003] In order to improve the bearing capacity and durability of spiral anchors, the engineering community has introduced grouting reinforcement technology. This technology injects cement slurry or chemical slurry into key locations such as the anchor plates, anchor rod side walls, and pile ends of the spiral anchor. It utilizes the penetration, compaction, and bonding effects of the slurry to improve the mechanical properties of the soil around the anchor body, enhance the soil-anchor interaction, and thus significantly improve the foundation's pull-out and compressive bearing capacity. In addition, grouting can effectively seal soil cracks, reduce groundwater erosion, and increase the service life of spiral anchors in corrosive environments. However, the existing spiral anchor grouting process still has many technical bottlenecks. At present, most projects still use single-point grouting or simple zoned grouting methods. Key parameters such as grouting pressure and flow rate are usually set based on construction experience, and lack scientific real-time monitoring and dynamic control methods.

[0004] For example, the application embodiment of the invention patent announcement with publication number: CN120276358A provides an industrial control task execution, image deployment method, equipment, medium and product, which relates to the field of computer technology. The method includes: obtaining the task logic corresponding to the target industrial control task; using the configuration interaction component corresponding to the industrial control algorithm to configure the operating parameters of the algorithm package of the industrial control algorithm based on the task logic; running at least one algorithm package of the industrial control algorithm in the target image to execute the target industrial control task. Since at least one algorithm package of the industrial control algorithm is deployed in the pre-built target image, the target image is obtained based on the operating environment required by the target industrial control task. Therefore, at least one algorithm to be deployed is deployed based on the target image to meet the requirements of the operating environment corresponding to the scenario to be built, so that the integration of various algorithms can be realized, and the various industrial control algorithms corresponding to the target industrial control task can be flexibly combined.

[0005] For example, the invention patent publication CN120255323A provides a controller parameter optimization method and task control method based on reinforcement learning, which relates to the field of control technology. The method includes: inputting the parameters of the PID controller for the current task into a DDPG model to obtain the parameters of the PID controller for the next task, and then inputting the parameters of the PID controller for the next task into the PID controller to obtain the control variable; determining the evaluation result of the PID controller's control based on the control variable as a reward; storing the state, action, reward of the current time step, and the state of the next time step as sample data in an experience pool; training the DDPG model based on the experience pool, and determining the target parameters output by the trained DDPG model as the optimal parameters of the PID controller. In the application stage, only the PID controller needs to output the target control variable based on the optimal parameters, without the involvement of the DDPG model, making the entire control model lightweight.

[0006] The above disclosed technical solutions have at least the following technical problems:

[0007] While existing industrial control task execution schemes achieve algorithm integration and flexible combination, they lack specialized designs for the screw anchor grouting process. While reinforcement learning-based control methods achieve dynamic optimization of PID parameters, they struggle to adapt to sudden changes in grouting conditions under complex geological conditions and lack a closed-loop feedback mechanism for geological parameter inversion. Neither of these existing technologies considers the collaborative control requirements of multi-channel grouting, failing to address key issues such as slurry crossflow and pressure imbalance common during the grouting process. They also lack the integration of construction expert experience and struggle to address the nonlinear characteristics of soil-slurry interactions during the grouting process. Furthermore, neither scheme employs a digital twin model to achieve virtual-real interactive optimization, resulting in a system lacking the ability to adapt to changing geological conditions in real time. Control parameter optimization in existing technologies primarily relies on offline training or preset rules, failing to achieve real-time dynamic coupled control of pressure, flow, and deformation during the grouting process, severely restricting the stability and reliability of grouting quality under complex geological conditions.

[0008] In view of the above problems, the present invention proposes a solution. Summary of the Invention

[0009] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a spiral anchor foundation grouting pressure-flow-deformation intelligent coupling control method, which solves the problem of poor adaptability of traditional spiral anchor foundation grouting technology to complex geology through the integration of multi-channel intelligent collaborative grouting system, fuzzy PID dynamic adjustment algorithm and digital twin feedback optimization technology.

[0010] To achieve the above object, the present invention provides the following technical solutions:

[0011] A method for intelligent coupling control of grouting pressure, flow and deformation of a spiral anchor foundation is characterized by comprising the following steps: matching a preset engineering parameter set according to the specification parameters of the spiral anchor and the type of soil in which it is located; collecting grouting data of each grouting channel, and calculating grouting deviation data in combination with the engineering parameter set; fuzzifying the grouting deviation data and converting it into fuzzy linguistic variables; inputting the fuzzy linguistic variables into a preset fuzzy rule base for reasoning, and outputting PID parameter corrections; dynamically adjusting the parameters of the PID controller according to the corrections to generate a pump speed adjustment instruction; executing the pump speed adjustment instruction and collecting the grouting data after execution; obtaining the soil permeability coefficient by inversion through constructing a digital twin model, and optimizing and updating the fuzzy rule base in combination with the grouting data after execution.

[0012] In a preferred embodiment, the engineering parameter set includes at least the target grouting pressure range, flow threshold, slurry diffusion model parameters and soil permeability coefficient; the grouting data includes real-time pressure, instantaneous flow and cumulative grouting volume data; the grouting deviation data includes pressure deviation and flow deviation.

[0013] In a preferred embodiment, the grouting deviation data is fuzzified and converted into fuzzy linguistic variables, specifically including: establishing a triangular and trapezoidal mixed membership function of pressure deviation and flow deviation; mapping the pressure deviation and flow deviation into the membership of a fuzzy set through the membership function; and dividing the fuzzy set into several levels of fuzzy linguistic variables according to the membership.

[0014] In a preferred embodiment, the preset fuzzy rule base is specifically constructed by: summarizing the optimal grouting parameter combinations under different soil conditions based on historical construction cases and geological survey data; obtaining an executable control strategy through expert experience based on the optimal grouting parameter combination; and designing a fuzzy rule base based on the executable control strategy.

[0015] In a preferred embodiment, the fuzzy linguistic variables are input into a preset fuzzy rule base for reasoning, and the PID parameter correction amount is output. Specifically, for each activated fuzzy control rule, its input variables are extracted, and the rule credibility weight is calculated through the membership value of the input variable; the PID parameter correction recommendation value output by each rule is multiplied by the corresponding weight to obtain a weighted correction amount; and the weighted correction amounts of all activated rules are arithmetic averaged to obtain the PID parameter correction amount.

[0016] In a preferred embodiment, the specific construction method of the digital twin model is: matching and integrating the collected grouting data of each channel with the engineering parameters to construct a dynamic analysis data set, and establishing a soil-slurry coupling model through the dynamic analysis data set; integrating the Levenberg-Marquardt algorithm with the soil-slurry coupling model to construct a digital twin model that can dynamically correct the soil permeability coefficient.

[0017] In a preferred embodiment, the updating of the fuzzy rule base is specifically as follows: extracting grouting deviation data and corresponding control results as sample data; iteratively optimizing the weights of each rule in the fuzzy rule base through a particle swarm optimization algorithm based on the sample data; integrating the optimized weights into the original fuzzy rule base, and updating the fuzzy rule base.

[0018] In a preferred embodiment, the establishment of the soil-slurry coupling model is specifically as follows: describing the relationship between foundation grouting pressure-flow-deformation through the coupling formula of the mechanical equilibrium equation and the slurry seepage equation; and constructing the soil-slurry coupling model according to the engineering parameters and the coupling formula.

[0019] In a preferred embodiment, the dynamic correction of the soil permeability coefficient is specifically as follows: the soil permeability coefficient provided by the engineering parameters is used as the initial reference value, and an error reduction formula is designed; the theoretical pressure distribution is calculated based on the current soil permeability coefficient, and compared and analyzed with the grouting data after execution, and the inverted soil permeability coefficient is iteratively updated according to the error reduction formula; in each iteration process, the relative change rate of the error function is calculated, and the iteration process is terminated when the relative change rate exceeds a preset convergence threshold, and the soil permeability coefficient is output.

[0020] The technical effects and advantages of the intelligent coupling control method for grouting pressure, flow rate and deformation of spiral anchor foundations provided by the present invention are as follows:

[0021] The present invention significantly improves the intelligence level and geological adaptability of spiral anchor foundation grouting construction by innovatively integrating a multi-channel intelligent collaborative grouting system, a fuzzy PID dynamic adjustment algorithm, and digital twin feedback optimization technology. This method can accurately perceive the slurry diffusion state under complex soil conditions and dynamically adjust the grouting parameters in real time, effectively avoiding common problems such as slurry channeling and pressure imbalance in traditional processes, and realizing multi-physical field intelligent coupling control of the grouting process. The fuzzy reasoning mechanism converts construction experience into executable control strategies, giving the system decision-making capabilities similar to those of human experts, while the digital twin technology constructs a simulation environment for virtual-real mapping, drives model inversion through real-time data, and continuously inverts soil layer parameters and corrects control rules to keep the grouting process in the optimal state. This adaptive adjustment feature not only greatly improves the stability of grouting quality, but also significantly enhances the bearing capacity of spiral anchor foundations, providing reliable technical support for foundation projects under complex geological conditions. It effectively solves the problem of poor adaptability of traditional spiral anchor foundation grouting processes to complex geology. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flow chart of a method for intelligent coupling control of pressure, flow and deformation of spiral anchor foundation grouting provided by an embodiment of the present invention.

[0023] Figure 2 This is a structural diagram of a spiral anchor provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0025] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0026] Example 1, Figure 1 The present invention provides a method for intelligently coupling pressure-flow-deformation control of spiral anchor foundation grouting, comprising the following steps:

[0027] S1, matching the preset engineering parameter set according to the specifications of the screw anchor and the type of soil;

[0028] S2, collect grouting data of each grouting channel and calculate grouting deviation data in combination with the engineering parameter set;

[0029] S3, fuzzy processing is performed on the grouting deviation data to convert it into fuzzy linguistic variables;

[0030] S4, input the fuzzy language variables into the preset fuzzy rule base for reasoning, and output the PID parameter correction value;

[0031] S5, dynamically adjust the parameters of the PID controller according to the correction amount and generate a pump speed adjustment instruction;

[0032] S6, executing the pump speed adjustment instruction and collecting the grouting data after execution;

[0033] S7, the soil permeability coefficient is obtained by inversion through building a digital twin model, and the fuzzy rule base is optimized and updated based on the grouting data after execution.

[0034] The present invention significantly improves the intelligence level and geological adaptability of spiral anchor foundation grouting construction by innovatively integrating a multi-channel intelligent collaborative grouting system, a fuzzy PID dynamic adjustment algorithm, and digital twin feedback optimization technology. This method can accurately perceive the slurry diffusion state under complex soil conditions and dynamically adjust the grouting parameters in real time, effectively avoiding common problems such as slurry channeling and pressure imbalance in traditional processes, and realizing multi-physical field intelligent coupling control of the grouting process. The fuzzy reasoning mechanism converts construction experience into executable control strategies, giving the system decision-making capabilities similar to those of human experts, while the digital twin technology constructs a simulation environment for virtual-real mapping, drives model inversion through real-time data, and continuously inverts soil layer parameters and corrects control rules to keep the grouting process in the optimal state. This adaptive adjustment feature not only greatly improves the stability of grouting quality, but also significantly enhances the bearing capacity of spiral anchor foundations, providing reliable technical support for foundation projects under complex geological conditions. It effectively solves the problem of poor adaptability of traditional spiral anchor foundation grouting processes to complex geology.

[0035] S1, matching the preset engineering parameter set according to the specifications of the screw anchor and the type of soil;

[0036] In this embodiment, the engineering parameter set includes at least the target grouting pressure range, flow threshold, slurry diffusion model parameters and soil permeability coefficient; the grouting data includes real-time pressure, instantaneous flow and cumulative grouting volume data; the grouting deviation data includes pressure deviation and flow deviation.

[0037] The embodiment of the present invention provides a spiral anchor structure diagram as shown in FIG. Figure 2 As shown in the figure, the specifications of spiral anchors require special consideration of the effects of bolt diameter and anchor plate spacing on bearing capacity. Tests show that the bearing capacity of spiral anchors increases with increasing bolt and plate diameters. Grouting is particularly effective for smaller diameter anchors (e.g., 89 mm), increasing their pullout bearing capacity by 58.49%. Larger diameter anchors (e.g., 180 mm) experience a 37.28% increase in strength. Regarding anchor plate spacing, within the range of (2.5-4.0)D (D is the outer diameter of the spiral anchor), the bearing capacity of ungrouted spiral anchors (UGSAs) varies by up to 18.75%, while the bearing capacity of grouting spiral anchors (GSAs) varies within 5%. Therefore, stricter anchor plate spacing control is required for UGSAs when presetting parameters.

[0038] Figure 2 middle Indicates the outer diameter of the screw anchor, Indicates the total length of the helical anchor, Indicates the size of the anchor connection part. Indicates the size of the spiral blade, Indicates the distance from the last spiral blade of the anchor rod to the anchor plate. Indicates the thickness of the anchor plate, Indicates the thickness of the spiral blade, represents the pitch of the spiral blades, Indicates diameter.

[0039] S2, collect grouting data of each grouting channel and calculate grouting deviation data in combination with the engineering parameter set;

[0040] In this embodiment, synchronous grouting is performed by grouting points set in the area between the anchor plates of the high-load forming spiral anchor, on the sides of the anchor rod, and at the pile end, including:

[0041] Independent grouting channels are set in the area between the anchor plates of the spiral anchor, the sides of the anchor rod and the pile end, and each channel corresponds to a different grouting point;

[0042] Automatically adjust the grouting sequence of each channel according to the soil permeability coefficient;

[0043] When the pressure in a certain channel drops suddenly, the flow rate in the adjacent channel will be automatically reduced.

[0044] The multi-channel, multi-point grouting method described above requires a design that incorporates a grouting-enhanced mechanical mechanism: Grouting can enhance friction by compacting the soil between the anchor plates and increasing the contact area between the anchor rod and the soil. Therefore, when establishing independent channels in the area between the anchor plates, on the sides of the anchor rod, and at the pile end, it is important to ensure that the spacing between the grouting points and the anchor plates is appropriate to maximize the grouting's "compaction-bonding" effect. Furthermore, torque changes should be recorded simultaneously during data collection, as torque is closely related to the bearing capacity of the screw anchor. The torque coefficient of the GSA is greater than that of the UGSA and decreases with increasing anchor rod diameter. Torque data can be used to assist in determining whether the grouting effect meets the required standards.

[0045] Permeability priority is determined by determining the soil permeability coefficient at each depth through pre-grouting tests or in-situ surveys. Grouting channels are then sorted in descending order of soil permeability coefficient. High-pressure grouting is prioritized in high-permeability areas to quickly fill pores. Low-frequency pulse grouting is used in low-permeability areas to avoid splitting damage.

[0046] When the pressure in a certain channel drops suddenly, it is determined that slurry is flowing or cracks are connected. The flow rate in the adjacent channel is immediately reduced to 50% of the baseline value, and the total grouting volume is redistributed through fuzzy reasoning to maintain overall pressure balance.

[0047] S3, fuzzy processing is performed on the grouting deviation data to convert it into fuzzy linguistic variables;

[0048] In this embodiment, the grouting deviation data is fuzzified and converted into fuzzy language variables, specifically including:

[0049] Establishing triangular and trapezoidal mixed membership functions of pressure deviation and flow deviation;

[0050] The pressure deviation and flow deviation are mapped to the membership of the fuzzy set through the membership function;

[0051] The fuzzy set is divided into several levels of fuzzy linguistic variables according to the degree of membership.

[0052] The grouting deviation data includes pressure deviation and flow deviation. The pressure deviation represents the difference between the real-time pressure of each channel and the pressure threshold of each grouting channel. The flow deviation represents the difference between the instantaneous flow of each channel and the flow threshold of each grouting channel.

[0053] This embodiment uses a fuzzy inference control method to map the real-time pressure deviation (ΔP) and flow deviation (ΔQ) data into five levels of fuzzy linguistic variables using a membership function: negative large (NB), negative small (NS), zero (ZE), positive small (PS), and positive large (PB). The domain of the pressure deviation is set to [-0.5, +0.5] MPa, and the domain of the flow deviation is set to [-10, +10] L / min. Fuzzification is achieved using a hybrid triangular and trapezoidal membership function. For example, when ΔP = -0.2 MPa, the fuzzification result is {NB: 0.5, NS: 0.5, ZE: 0, PS: 0, PB: 0}; when ΔQ = +3 L / min, the fuzzification result is {NB: 0, NS: 0, ZE: 0, PS: 0.25, PB: 0.25}.

[0054] The pre-set fuzzy rule base needs to incorporate analysis of the failure modes of spiral anchors. When the depth-to-diameter ratio (H / D) of the first anchor plate of a spiral anchor is small, radial cracks first develop in the UGSA before circumferential cracks develop, while circumferential cracks first develop in the GSA before expanding into radial cracks. Therefore, the rule base needs to incorporate differentiated control strategies for different H / D ratios: when H / D ≤ 5.25 (the GSA cracking threshold), the grouting rate needs to be reduced to prevent rapid crack formation; when H / D > 6.25, the pressure can be increased to enhance soil compaction.

[0055] S4, input the fuzzy language variables into the preset fuzzy rule base for reasoning, and output the PID parameter correction value;

[0056] In this embodiment, the specific construction method of the preset fuzzy rule base is as follows:

[0057] Based on historical construction cases and geological survey data, the optimal grouting parameter combinations under different soil conditions are summarized;

[0058] Obtain executable control strategies based on the optimal grouting parameter combination through expert experience;

[0059] Design a fuzzy rule base based on executable control strategies.

[0060] In this embodiment, the fuzzy linguistic variables are input into a preset fuzzy rule base for reasoning, and the PID parameter correction amount is output, specifically:

[0061] For each activated fuzzy control rule, its input variables are extracted and the rule credibility weight is calculated through the membership value of the input variables;

[0062] Multiply the PID parameter correction recommendation value output by each rule by the corresponding weight to obtain the weighted correction amount;

[0063] The PID parameter correction amount is obtained by performing arithmetic averaging on the weighted correction amounts of all activated rules.

[0064] S5, dynamically adjust the parameters of the PID controller according to the correction amount and generate a pump speed adjustment instruction;

[0065] S6, executing the pump speed adjustment instruction and collecting the grouting data after execution;

[0066] S7, the soil permeability coefficient is obtained by inversion through building a digital twin model, and the fuzzy rule base is optimized and updated based on the grouting data after execution.

[0067] In this embodiment, the specific method for constructing the digital twin model is:

[0068] The collected grouting data of each channel is matched and integrated with the engineering parameters to construct a dynamic analysis data set, and a soil-grout coupling model is established based on the dynamic analysis data set;

[0069] The Levenberg-Marquardt algorithm is integrated with the soil-slurry coupling model to construct a digital twin model that can dynamically correct the soil permeability coefficient.

[0070] In this embodiment, the updating of the fuzzy rule base is specifically as follows:

[0071] Extract grouting deviation data and corresponding control results as sample data;

[0072] According to the sample data, the weight of each rule in the fuzzy rule base is iteratively optimized by particle swarm optimization algorithm;

[0073] Integrate the optimized weights into the original fuzzy rule base and update the fuzzy rule base.

[0074] In this embodiment, the soil-slurry coupling model is established as follows:

[0075] The relationship between foundation grouting pressure, flow rate and deformation is described by coupling the mechanical equilibrium equation and the grout seepage equation.

[0076] According to engineering parameters and coupling formulas, a soil-slurry coupling model is constructed.

[0077] In this embodiment, the dynamic correction of soil permeability coefficient is specifically:

[0078] The soil permeability coefficient provided by the engineering parameters is used as the initial reference value and the error reduction formula is designed;

[0079] The theoretical pressure distribution is calculated based on the current soil permeability coefficient, and compared with the grouting data after execution. The inverted soil permeability coefficient is iteratively updated according to the error reduction formula;

[0080] In each iteration, the relative change rate of the error function is calculated. When the relative change rate exceeds the preset convergence threshold, the iteration process is terminated and the soil permeability coefficient is output.

[0081] Grouting deviation data refers to the grouting data when there is a significant deviation between the actual monitoring data and the engineering parameters during the grouting process.

[0082] The formula for adjusting rule weights based on the particle swarm algorithm is:

[0083]

[0084] in, For the The new weights of the fuzzy rules, For the The old weights of the fuzzy rules, is the forgetting factor (used to attenuate the influence of early atypical working condition data on the current rule weight during the screw anchor grouting process), For the The adaptability of each particle to the screw anchor grouting, the adaptability indicators include pressure fluctuation amplitude and flow deviation rate, For the The particle is The candidate weights generated by the rules.

[0085] The particle swarm optimization algorithm (PSO) is a swarm intelligence optimization algorithm that simulates the collaborative search of particles in the solution space to find the optimal solution. Its core principle is to treat each potential solution as a "particle" with a position and velocity. During the iteration process, the particle dynamically adjusts its position to move toward two goals: its own historical optimal position and the historical optimal position of the entire particle swarm. The basic algorithm process is as follows: first, the position and velocity of the particle swarm are initialized. Then, the fitness value of each particle is calculated (which measures the adaptability of the control strategy corresponding to the particle to screw anchor grouting. Adaptability indicators include pressure fluctuation amplitude and flow deviation rate). Individual and global extreme values ​​are updated. Then, the particle velocity and position are updated according to the formula. This iteration continues until the termination condition is met (such as reaching the maximum number of iterations or the optimal solution accuracy is met).

[0086] For each activated fuzzy control rule, the rule credibility weight is calculated according to the membership value of its input variable. The calculation formula is:

[0087]

[0088] in, Indicates the The credibility weight of the activated rule, Indicates the Rule No. The membership values ​​of the input variables, The total number of variables for inputting the spiral anchor grouting control strategy.

[0089] Multiply the PID parameter correction recommendation value output by each rule by the weight of each rule to obtain the weighted correction amount. Perform arithmetic averaging on the weighted correction amounts of all activated rules to obtain the final PID parameter correction amount. The PID parameter correction amount calculation formula is:

[0090]

[0091] in, is the comprehensive correction value, is the total number of activated screw anchor grouting control strategy rules, For the The PID parameter correction recommended value output by the rule, Indicates the The credibility weight of the activated rule.

[0092] In this embodiment, the establishment of the soil-slurry coupling model is specifically: constructing a three-dimensional dynamic calculation model, which describes the complex relationship between these physical phenomena through a set of interrelated mathematical equations, and sets the model parameters according to the engineering parameters.

[0093] The mechanical equilibrium equation in the soil-slurry coupling model is:

[0094]

[0095] in, is the effective stress tensor, is the Biot effective stress coefficient, is the pore pressure, is the mixture density, is the divergence operator (representing the spatial distribution change of the stress tensor), is the gravitational acceleration vector, is the soil displacement vector, For time.

[0096] The slurry seepage equation in the soil-slurry coupling model is:

[0097]

[0098] in, is the porosity, is the slurry saturation, is the absolute permeability, is the relative permeability, is the slurry dynamic viscosity, is the divergence operator (representing the spatial distribution change of the stress tensor), is the slurry pressure, It is the slurry source and sink item (indicating the flow rate of grouting or pumping, a positive value represents injection).

[0099] The coupling formula is:

[0100]

[0101] in, is the capillary pressure, is the pore pressure, is the slurry pressure.

[0102] The convergence threshold is a pre-set extremely small positive number used to determine whether the relative rate of change of the error function is small enough to confirm that the algorithm has reached a stable solution. When the relative rate of change of the error function is less than the convergence threshold, the iteration is terminated.

[0103] The relative rate of change of the error function is a key indicator for determining whether the Levenberg-Marquardt algorithm has converged. The calculation formula is:

[0104]

[0105] in, is the relative rate of change of the error function, is the number of monitoring points, is the inverse soil permeability coefficient, For the The model predicts the pressure at the iteration, For the The actual monitored pressure at the iteration.

[0106] The formula for reducing the error between the model-predicted pressure and the actual monitored pressure by inverting the soil permeability coefficient using the Levenberg-Marquardt algorithm is:

[0107]

[0108] in, is the relative rate of change of the error function, is the inverse soil permeability coefficient, Predict pressure for the model, To actually monitor the pressure.

[0109] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0110] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0111] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0112] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0113] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0114] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for intelligent coupling control of pressure, flow rate and deformation of screw anchor foundation grouting, characterized in that: The following steps are involved: Match the preset engineering parameter set according to the specifications of the screw anchor and the type of soil in which it is located; Collect grouting data of each grouting channel and calculate grouting deviation data in combination with the engineering parameter set; The grouting deviation data is fuzzified and converted into fuzzy linguistic variables, specifically including: establishing a triangular and trapezoidal mixed membership function of pressure deviation and flow deviation, mapping the pressure deviation and flow deviation into the membership of a fuzzy set through the membership function, and dividing the fuzzy set into several levels of fuzzy linguistic variables according to the membership; Input the fuzzy language variables into the preset fuzzy rule base for reasoning and output the PID parameter correction value; Dynamically adjust the parameters of the PID controller according to the correction value to generate a pump speed adjustment instruction; Execute pump speed adjustment instructions and collect grouting data after execution; The soil permeability coefficient is obtained by inversion through constructing a digital twin model, and the fuzzy rule base is optimized and updated in combination with the grouting data after execution. The specific construction method of the digital twin model is as follows: the collected grouting data of each channel is matched and integrated with the engineering parameters to construct a dynamic analysis data set. The soil-slurry coupling model is established through the dynamic analysis data set. The Levenberg-Marquardt algorithm is integrated with the soil-slurry coupling model to construct a digital twin model that can dynamically correct the soil permeability coefficient.

2. The spiral anchor foundation grouting pressure-flow-deformation intelligent coupling control method according to claim 1 is characterized in that: The engineering parameter set includes at least the target grouting pressure range, flow threshold, slurry diffusion model parameters and soil permeability coefficient; the grouting data includes real-time pressure, instantaneous flow and cumulative grouting volume data; the grouting deviation data includes pressure deviation and flow deviation.

3. The intelligent coupling control method for spiral anchor foundation grouting pressure-flow-deformation according to claim 2 is characterized in that: The specific construction method of the preset fuzzy rule base is as follows: Based on historical construction cases and geological survey data, the optimal grouting parameter combinations under different soil conditions are summarized; Obtain executable control strategies based on the optimal grouting parameter combination through expert experience; Design a fuzzy rule base based on executable control strategies.

4. The intelligent coupling control method for spiral anchor foundation grouting pressure-flow-deformation according to claim 3 is characterized in that: The fuzzy language variables are input into the preset fuzzy rule base for reasoning, and the PID parameter correction amount is output, specifically: For each activated fuzzy control rule, its input variables are extracted and the rule credibility weight is calculated through the membership value of the input variables; Multiply the PID parameter correction recommendation value output by each rule by the corresponding weight to obtain the weighted correction amount; The PID parameter correction amount is obtained by performing arithmetic averaging on the weighted correction amounts of all activated rules.

5. The intelligent coupling control method for spiral anchor foundation grouting pressure-flow-deformation according to claim 4 is characterized in that: The updating fuzzy rule base is specifically as follows: Extract grouting deviation data and corresponding control results as sample data; According to the sample data, the weight of each rule in the fuzzy rule base is iteratively optimized by particle swarm optimization algorithm; Integrate the optimized weights into the original fuzzy rule base and update the fuzzy rule base.

6. The intelligent coupling control method for spiral anchor foundation grouting pressure-flow-deformation according to claim 5 is characterized in that: The soil-slurry coupling model is established as follows: The relationship between foundation grouting pressure, flow rate and deformation is described by coupling the mechanical equilibrium equation and the grout seepage equation. According to engineering parameters and coupling formulas, a soil-slurry coupling model is constructed.

7. The intelligent coupling control method for spiral anchor foundation grouting pressure-flow-deformation according to claim 6 is characterized in that: The dynamic correction soil permeability coefficient is specifically: The soil permeability coefficient provided by the engineering parameters is used as the initial reference value and the error reduction formula is designed; The theoretical pressure distribution is calculated based on the current soil permeability coefficient, and compared with the grouting data after execution. The inverted soil permeability coefficient is iteratively updated according to the error reduction formula; In each iteration, the relative change rate of the error function is calculated. When the relative change rate exceeds the preset convergence threshold, the iteration process is terminated and the soil permeability coefficient is output.

Images