Anchor rod self-adaptive grouting control system

Abstract

The invention discloses an anchor rod self-adaptive grouting control system, which comprises an environmental parameter collection module, a grouting control module, a grouting control module and a grouting control module, and is characterized in that the environmental parameter collection module is used for collecting construction environmental parameters and consolidation strength data; the initial parameter prediction module is used for inputting the construction environment parameters and the consolidation strength data into a pre-constructed initial parameter prediction model and outputting initial parameters; the grouting data collection module is used for numbering the N anchor rods to obtain the numbers of the anchor rods; the N anchor rods are grouted according to the initial parameters; and establishing an intelligent sensing collection network to collect monitoring data, and summarizing the monitoring data to the central adaptive regulation and control module. According to the invention, by integrating environmental parameter monitoring, intelligent data processing and self-adaptive control algorithms, the efficiency and safety of grouting construction are improved, so that the overall quality and durability of a project are improved.

Description

Technical Field

[0001] This application relates to the field of automation control technology, and particularly to an adaptive grouting control system for anchor bolts. Background Art

[0002] The construction process of the anchor bolt grouting process generally includes the following: According to the requirements of the grouting process, the corresponding grouting equipment and grouting materials are configured. The grouting materials are injected into the anchor bolt holes through a grouting pump. During the grouting process, the grouting speed, grouting volume, and grouting pressure need to be controlled to ensure that the grouting materials can evenly fill the entire hole. After grouting, the consolidation time of the grouting materials needs to be controlled to ensure that the grouting materials can be completely consolidated and form a firm connection. After the grouting process is completed, the grouting effect is detected and evaluated.

[0003] However, nowadays, the grouting parameters of the anchor bolt grouting process, such as the grouting pressure and grouting volume, are still calculated relying on manual experience. If intermittent grouting is to be carried out, the intermittent time even more needs to rely on manual experience for estimation. However, when facing multi-anchor bolts or batch grouting operations, due to the flexibility and accuracy problems of manual experience, the efficiency and safety of the grouting construction often have problems, resulting in huge trial-and-error costs for the implementation of the grouting design. Summary of the Invention

[0004] In order to solve the above problems, an embodiment of the present invention provides an adaptive grouting control system for anchor bolts, and the system includes:

[0005] An environmental parameter collection module, which is used to collect construction environmental parameters and consolidation strength data;

[0006] An initial parameter prediction module, which is used to input the construction environmental parameters and consolidation strength data into a pre-constructed initial parameter prediction model and output initial parameters;

[0007] A grouting data collection module, which is used to number N anchor bolts to obtain anchor bolt numbers; the N anchor bolts are grouted according to the initial parameters; a smart sensing collection network is established to collect monitoring data, and the monitoring data is summarized to a central adaptive control module;

[0008] A central adaptive control module, which uses the monitoring data to obtain grouting adjustment parameters;

[0009] A grouting control module, which is used to transmit the grouting adjustment parameters back to the anchor bolt control unit of the corresponding anchor bolt number through the smart sensing collection network, and the anchor bolt control unit adjusts the grouting parameters according to the grouting adjustment parameters;

[0010] The human-computer interaction module adopts a graphical user interface for manual operations.

[0011] Furthermore, the training method of the initial parameter prediction model includes:

[0012] Taking all construction environment parameters and consolidation strength data as the input of the initial parameter prediction model, the initial parameter prediction model outputs the predicted initial parameters corresponding to each group of construction environment parameters and consolidation strength data, taking the actual initial parameters corresponding to each group of construction environment parameters and consolidation strength data as the prediction target, and taking the minimization of the sum of the first prediction accuracies of all predicted initial parameters as the training target; training the initial parameter prediction model until the sum of the first prediction accuracies reaches convergence and then stopping the training; the initial parameter prediction model is a convolutional neural network model.

[0013] Furthermore, the intelligent sensing collection network includes N edge computing nodes and a central processing server. The central processing server receives the monitoring data of the N edge computing nodes and filters the monitoring data using the Kalman filter joint model.

[0014] Furthermore, the modeling method of the Kalman filter joint model includes:

[0015] Constructing a state equation, the state equation includes:

[0016] ;

[0017] In the formula, is the state vector of the th anchor bolt at time ; is the state transition matrix; is the control input matrix; is the control input; is the process noise, following a Gaussian noise with a mean of 0 and a covariance of ; and are the anchor bolt numbers, and 0 < ≤ N, 0 < ≤ N;

[0018] Constructing an observation equation, the observation equation includes:

[0019] ;

[0020] In the formula, is the observation value of the th anchor bolt; is the observation matrix; is the observation noise, adopting a Gaussian white noise model with a mean of 0 and a covariance of 。

[0021] Furthermore, the filtering method of the Kalman filter joint model includes:

[0022] Using the state prediction equation, obtain the predicted state value of the th anchor bolt at time ;

[0023] Using the error covariance prediction equation, obtain the predicted error covariance matrix of the th anchor bolt at time ;

[0024] By combining the predicted error covariance, the observation matrix, the observation equation, and the covariance of the observation noise,

[0025] obtain the Kalman gain;

[0026] Calculate the residual. After obtaining the residual, update the predicted value through the state update equation to obtain the updated predicted state value, and at the same time use the error covariance update equation to update the error covariance according to the Kalman gain.

[0027] Furthermore, the method for obtaining the grouting adjustment parameters includes: dividing the monitoring data into N data regions based on the anchor bolt numbers, using an optimization algorithm to determine the target grouting volume of each anchor bolt, fusing the target grouting volume with the data region to which the anchor bolt number belongs into a data special zone, and inputting the data special zone into a pre-constructed adaptive control model to output the grouting adjustment parameters.

[0028] Furthermore, the method for obtaining the target grouting volume includes:

[0029] Initialize the particle swarm. Each particle represents a combination of target grouting volumes, with a length of N;

[0030] Calculate the fitness value using the fitness function;

[0031] Update the particle positions and velocities using the position update equation and the velocity update equation, and perform iterative calculations. In each iteration, recalculate the fitness value of each particle. If the termination condition is reached, terminate the iteration. The termination conditions include:

[0032] Reaching the maximum number of iterations; the change in the global best fitness is less than the preset threshold.

[0033] Furthermore, the training method of the adaptive control model includes:

[0034] All data zones are used as the input of the adaptive control model. The adaptive control model outputs the predicted grouting adjustment parameters corresponding to each group of data zones. The actual grouting adjustment parameters corresponding to each group of data zones are used as the prediction target, and minimizing the sum of the second prediction accuracies of all predicted grouting adjustment parameters is used as the training target. The adaptive control model is trained until the sum of the second prediction accuracies converges, and then the training stops. The adaptive control model is a support vector machine.

[0035] Technical effects and advantages of an anchor bolt adaptive grouting control system provided by the present invention:

[0036] By integrating environmental parameter monitoring, intelligent data processing, and adaptive control algorithms, the present invention improves the efficiency and safety of grouting construction, thereby enhancing the overall quality and durability of the project. The real-time monitoring of construction environmental parameters (such as temperature, humidity, air pressure, and soil type) by the present invention ensures that the grouting process can adapt to actual construction conditions. Different environmental factors have a significant impact on the performance of grouting materials, and accurate data collection helps to adjust construction parameters, thereby improving grouting quality. By inputting construction environmental parameters and consolidation strength data into the initial parameter prediction model, the required grouting volume, pressure, and ratio of the anchor bolt before construction can be efficiently estimated, ensuring that the requirements of the project can be met at the initial stage and laying a good foundation for subsequent construction. By continuously monitoring the state of each anchor bolt through the intelligent sensing collection network, real-time data can be quickly obtained, and then the data is analyzed by the central adaptive control module to provide accurate grouting adjustment parameters. The data-driven decision-making mechanism can effectively respond to the changes and uncertainties that may occur during the construction process. Using machine learning and optimization algorithms to train and update the system can continuously improve the prediction accuracy and adaptability of the system. Introducing the Kalman filter joint model to process the data interaction between multiple anchor bolts can more comprehensively consider the mutual influence between each anchor bolt, thereby providing more accurate state estimation and decision support when dealing with noise and uncertainties. Description of the Drawings

[0037] Figure 1 It is a connection schematic diagram of an anchor bolt adaptive grouting control system in Embodiment 1;

[0038] Figure 2 It is a connection schematic diagram of the intelligent sensing collection network in Embodiment 2; Detailed Embodiment

[0039] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0040] Embodiment 1:

[0041] Please refer to Figure 1 As shown, a bolt adaptive grouting control system in this embodiment includes:

[0042] An environmental parameter collection module that collects construction environmental parameters and consolidation strength data;

[0043] An initial parameter prediction module that inputs the construction environmental parameters and consolidation strength data into a pre-constructed initial parameter prediction model and outputs initial parameters;

[0044] A grouting data collection module that numbers N bolts to obtain bolt numbers; the N bolts are grouted according to the initial parameters; an intelligent sensing collection network is established to collect monitoring data, and the monitoring data is summarized to a central adaptive control module;

[0045] A central adaptive control module that obtains grouting adjustment parameters using the monitoring data;

[0046] A grouting control module that transmits the grouting adjustment parameters back to the bolt control unit of the corresponding bolt number through the intelligent sensing collection network, and the bolt control unit adjusts the grouting parameters according to the grouting adjustment parameters;

[0047] A human-machine interaction module that uses a graphical user interface for manual operations.

[0048] The graphical user interface (GUI) displays real-time monitoring data, system status, and grouting parameters, which can help users quickly understand and operate the system. The human-machine interaction module serves as an input window for preset values, allowing users to manually input or adjust certain parameters (such as the target grouting volume, construction environmental parameters), and feedback this information to the system to prompt model update and optimization.

[0049] The construction environment parameters include temperature, humidity, air pressure, and a preset soil type. Temperature and humidity are measured using sensors. The temperature of the environment and the soil affects the rheological properties and curing time of the grouting material. Air humidity and soil water content affect the performance of the grouting material. The air pressure is mainly used to determine the pressure range. The impacts of low altitude and high altitude on construction conditions are different. The preset soil types include clay, sand, gravel, etc. Different soil types also have different effects on the permeability of the grouting material. The consolidation strength data includes consolidation strength, soil porosity ratio, and pore water pressure. The consolidation strength data is directly related to the bearing capacity and stability of the anchor rod. Among them, the consolidation strength is the shear strength of the soil under certain conditions, which is used to characterize the stability of the soil. The soil porosity ratio is the ratio of the volume of soil pores to the volume of solid particles, which affects the consolidation process and strength of the soil. The pore water pressure is the pressure of water inside the soil, which is crucial for consolidation and bearing capacity. A pore water pressure gauge (such as a piezoelectric water pressure gauge) can be used for monitoring.

[0050] The training method of the initial parameter prediction model includes:

[0051] Taking all construction environment parameters and consolidation strength data as the input of the initial parameter prediction model, the initial parameter prediction model outputs the predicted initial parameters corresponding to each group of construction environment parameters and consolidation strength data, taking the actual initial parameters corresponding to each group of construction environment parameters and consolidation strength data as the prediction target, and taking minimizing the sum of the first prediction accuracies of all predicted initial parameters as the training target.

[0052] Among them, the calculation formula for the first prediction accuracy is: , where is the number of each group of construction environment parameters and consolidation strength data, is the first prediction accuracy, is the predicted initial parameter corresponding to the construction environment parameters and consolidation strength data of the is the actual initial parameter corresponding to the construction environment parameters and consolidation strength data of the

[0053] The initial parameters include grouting volume, grouting speed, grouting pressure, slurry ratio, and intermittent time. Among them, the slurry ratio is a fixed ratio. The fixed ratio can be the predicted value output by the initial parameter prediction model or a preset value. If there is no preset value of the fixed ratio, the initial parameter is the predicted value output by the initial parameter prediction model. If there is a preset value of the fixed ratio, the initial parameter is the preset value of the fixed ratio. The intermittent time is because intermittent grouting requires intentional interruption of grouting.

[0054] Specifically, the initial parameters are range values, which serve as the safety range before the start of the bolt grouting construction. Correct initial parameters can ensure the grouting quality, enhance the anchoring effect of the bolts, improve the construction safety and the durability of the project. After grouting, integrated adjustment will be carried out for each bolt.

[0055] The method for obtaining the grouting adjustment parameters includes: dividing the monitoring data into N data areas based on the bolt numbers, using an optimization algorithm to determine the target grouting volume for each bolt, integrating the target grouting volume with the data area to which the bolt number belongs into a data special area, and inputting the data special area into a pre-constructed adaptive control model to output the grouting adjustment parameters.

[0056] The data areas include grouting volume, grouting speed, grouting pressure, slurry ratio and intermittent time;

[0057] By dividing the monitoring data into multiple data areas, it is possible to better analyze and process the characteristics of different bolts; each bolt may exhibit different behaviors due to factors such as its specific location, construction conditions or environment, so this division can help optimize the grouting volume and adjustment parameters.

[0058] The data areas include grouting volume, grouting speed, grouting pressure, slurry ratio and intermittent time;

[0059] The data special area includes target grouting volume, grouting volume, grouting speed, grouting pressure, slurry ratio and intermittent time;

[0060] The construction of the data special area makes the data input into the adaptive control model more comprehensive and rich, and thus allows the model to better understand the relationship between the target state and the actual state of each bolt; without the integration of the target grouting volume, the model may not be able to comprehensively evaluate the bolt performance and the parameters required for adjustment.

[0061] The data special area includes target grouting volume, grouting volume, grouting speed, grouting pressure, slurry ratio and intermittent time;

[0062] The monitoring data includes grouting volume, grouting speed, grouting pressure, slurry ratio and intermittent time;

[0063] Specifically, the initial parameters are range values, and the monitoring data are accurate values. The monitoring data are collected after grouting and are the data measured in actual operation, so they are accurate values.

[0064] N is the preset number of bolts, representing the number of bolts in the working state.

[0065] The method for obtaining the target grouting volume includes:

[0066] Initializing the particle swarm, where each particle represents a combination of target grouting volumes, with a length of N;

[0067] Calculate the fitness value using the fitness function ;

[0068] The fitness function includes:

[0069] ;

[0070] In the formula, is the bolt number, is the particle number, and 0 < ≤ N, 0 < ≤ N; is the weight of the th bolt, which is preset according to construction requirements or importance.

[0071] Among them, the target state is the ideal bolt performance index set based on engineering requirements or design standards, usually the desired state, including:

[0072] Displacement: The maximum allowable displacement after bolt grouting under preset conditions.

[0073] Stress: The maximum stress that the bolt should bear under preset conditions.

[0074] Grouting pressure: To achieve the optimal grouting pressure under preset conditions, so as to improve the consolidation strength and bearing capacity of the bolt.

[0075] Grouting volume: Under preset conditions, the grouting volume reaches the target grouting volume, and the target grouting volume is a preset value.

[0076] Stability index: Requirements for the interaction force between the bolt and the surrounding soil.

[0077] The actual state is the performance index of the bolt under the actual operating conditions on site obtained through monitoring equipment, which reflects the true performance of the bolt during actual construction or use.

[0078] The purpose of the optimization algorithm is to strive to make the actual state close to or reach the target state by adjusting the grouting volume of each bolt.

[0079] Update the particle position and velocity using the position update equation and velocity update equation, and perform iterative calculations. In each iteration, recalculate the fitness value of each particle. If the termination condition is reached, terminate the iteration. The termination conditions include:

[0080] Reach the maximum number of iterations; The change in the global best fitness is less than the preset threshold (i.e., convergence).

[0081] It should be noted that reaching one of the termination conditions is the termination condition, and it is not mandatory to meet both conditions.

[0082] The position update equation includes:

[0083] ;

[0084] Wherein, is the position of the th particle in the th iteration; is the number of iterations. is the velocity of the th particle in the th iteration.

[0085] The velocity update equation includes:

[0086] ;

[0087] Wherein, is the inertia weight, which controls the influence degree of the historical velocity of the particle on the current velocity; and are learning factors, usually positive values, indicating the tendency of the particle to learn from the individual best position and the global best position ; and are random numbers within the range of [0, 1], which are used to increase the randomness and diversity of the search.

[0088] The reason for first confirming the single grouting volume is that by determining the grouting volume first, the trial-and-error cost of adjustment during the construction process can be reduced, and the impact on subsequent readjustment can be minimized. Analyzing the relationship data between the grouting volume and the effect helps to make more accurate subsequent plans, and the human-computer interaction effect is also the best.

[0089] The training method of the adaptive control model includes:

[0090] Taking all data zones as the input of the adaptive control model, the adaptive control model outputs the corresponding grouting adjustment parameters predicted for each group of data zones, takes the actual grouting adjustment parameters corresponding to each group of data zones as the prediction target, and takes minimizing the sum of the second prediction accuracies of all predicted grouting adjustment parameters as the training target.

[0091] Among them, the calculation formula of the second prediction accuracy is: , where is the number of each group of data zones, is the second prediction accuracy, is the predicted grouting adjustment parameter corresponding to the th data zone, is the The actual grouting adjustment parameters corresponding to the group data area; train the adaptive control model until the sum of the second prediction accuracies reaches convergence; the adaptive control model is a support vector machine.

[0092] The adaptive control model can be adjusted in real time according to new input data, enhancing the sensitivity of the system to environmental changes. For example, if the actual grouting effect monitored does not match the expectation, the model can quickly adjust the prediction parameters to reflect the new construction state.

[0093] The bolt control unit is a device or module specifically used to control and adjust the bolt grouting process. By receiving the grouting adjustment parameters from the central adaptive control module, it controls important parameters such as the grouting volume, grouting pressure, and flow rate related to the bolt to ensure that the bolt meets the established performance standards during construction; after receiving the instructions from the central adaptive control module, the bolt control unit can perform specific operations, such as starting or stopping the grouting process, adjusting the grouting pressure or flow rate, etc. It can convert the system decision into actual operations, making the grouting process more automated and efficient.

[0094] Embodiment 2:

[0095] As Figure 2 shown, the intelligent sensing collection network includes N edge computing nodes and a central processing server. A variety of sensor devices (such as high-precision instruments like pressure sensors and flow meters) are attached to the bolts to obtain multi-dimensional data of the bolts and the surrounding environment. One bolt is an edge computing node, and the edge computing nodes and the central processing server use low-power wide-area network technology or 5G technology for data transmission. The central processing server is connected to the human-computer interaction module. The central processing server receives the monitoring data of the N edge computing nodes and filters the monitoring data. Given that there are N edge computing nodes and there may be interference between them, a single Kalman filter may not be sufficient to effectively process the correlation between the states of each bolt. Therefore, a Kalman filter joint model is used for filtering.

[0096] The modeling method of the Kalman filter joint model includes:

[0097] Construct the state equation:

[0098] For the th bolt, assume the state vector of the bolt is , which includes quantities such as pressure, flow rate, and displacement. Assume that there is an interaction between the states of N bolts, and this influence is defined through the state transition matrix. The state equation includes:

[0099] ;

[0100] In the formula, is the The state vector of the th anchor bolt at time is the state transition matrix, which describes the influence of the th anchor bolt on the th anchor bolt; is the control input matrix, which is used to describe the influence of the control input on the state of the th anchor bolt; is the control input (such as external stress, etc.); is the process noise, which is assumed to follow a Gaussian noise with a mean of 0 and a covariance of ; and are the anchor bolt numbers, and 0 < ≤ N, 0 < ≤ N;

[0101] Construct the observation equation:

[0102] The readings of each anchor bolt are also affected by other anchor bolts. The observation equation includes:

[0103] ;

[0104] In the formula, is the observation value of the th anchor bolt; is the observation matrix, which describes the influence of the state of the th anchor bolt on the observation of the th anchor bolt; is the observation noise. The Gaussian white noise model is adopted, and it is assumed that the mean is 0 and the covariance is .

[0105] The filtering method of the Kalman filter joint model includes:

[0106] Use the state prediction equation to obtain the predicted state value of the th anchor bolt at time , and the state prediction equation includes:

[0107] ;

[0108] In the formula, is the latest state estimate (updated state) of the th anchor bolt at time , which is used to calculate the predicted state.

[0109] Use the error covariance prediction equation to obtain the predicted error covariance matrix of the th anchor bolt at time , and the error covariance prediction equation includes:

[0110] ;

[0111] Wherein, is the error covariance matrix of the th anchor bolt at time ; is the transpose symbol.

[0112] By combining the predicted error covariance, the observation matrix, the observation equation and the covariance of the observation noise, the Kalman gain is obtained; the calculation method of the Kalman gain includes:

[0113] ;

[0114] Calculate the residual (i.e., the difference between the observed value and the predicted value). After obtaining the residual, update the predicted value through the state update equation to obtain the updated predicted state value , and at the same time update the error covariance according to the Kalman gain using the error covariance update equation .

[0115] The state update equation includes:

[0116] ;

[0117] The error covariance update equation includes:

[0118] ;

[0119] Wherein, is the identity matrix.

[0120] The Kalman filter joint model can perform state estimation on multiple interacting anchor bolts, comprehensively consider the interference and correlation between each anchor bolt, use the linear state equation and the observation equation, and optimize the overall estimation of the system through the prediction and update mechanism, especially showing superiority in the presence of noise and uncertainty.

[0121] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

[0122] The above are only the preferred specific embodiments of the embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application, according to the technical solution and its concept of the present application, makes equivalent substitutions or changes, and should be covered by the protection scope of the present application.

Claims

1. An anchor rod adaptive grouting control system, characterized in that, include: An environmental parameter collection module, which is used to collect construction environmental parameters and consolidation strength data; An initial parameter prediction module, which is used to input construction environment parameters and consolidation strength data into a pre-built initial parameter prediction model and output initial parameters; A grouting data collection module, wherein the grouting data collection module is used to number N anchor rods and obtain anchor rod numbers; N anchors are grouted according to the initial parameters; Establish an intelligent sensor collection network to collect monitoring data and aggregate the monitoring data to the central adaptive control module; A central adaptive control module, wherein the central adaptive control module uses monitoring data to obtain grouting adjustment parameters; A grouting control module, which is used to transmit the grouting adjustment parameters back to the anchor control unit of the corresponding anchor number through the intelligent sensor collection network, and the anchor control unit adjusts the grouting parameters according to the grouting adjustment parameters; A human-computer interaction module adopts a graphical user interface for manual operation.

2. The self - adaptive grouting control system for an anchor rod according to claim 1, wherein, The training method of the initial parameter prediction model includes: All construction environment parameters and consolidation strength data are used as inputs of the initial parameter prediction model. The initial parameter prediction model takes the initial parameters corresponding to each set of construction environment parameters and consolidation strength data as outputs, takes the actual initial parameters corresponding to each set of construction environment parameters and consolidation strength data as prediction targets, and takes minimizing the sum of the first prediction accuracies of all predicted initial parameters as the training target; the initial parameter prediction model is trained until the sum of the first prediction accuracies converges; the initial parameter prediction model is a convolutional neural network model.

3. The self - adaptive grouting control system for an anchor rod according to claim 1, wherein, The intelligent sensor collection network includes N edge computing nodes and a central processing server. The central processing server receives monitoring data from the N edge computing nodes and filters the monitoring data using a Kalman filter joint model.

4. The self-adaptive grouting control system for an anchor rod according to claim 3, wherein, The modeling method of the Kalman filter joint model includes: Construct the state equation, which includes: ； Wherein, is the th state vector of the th anchor bolt at time is the state transition matrix; is the control input matrix; is the control input; is the process noise, which follows a Gaussian noise with a mean of 0 and a covariance of ; and are the anchor bolt numbers, and 0 < ≤ N, 0 < ≤ N; Construct the observation equation, which includes: ； In the formula, is the observed value of the th anchor bolt; is the observation matrix; is the observation noise, adopting a Gaussian white noise model, with a mean of 0 and a covariance of .

5. An anchor rod adaptive grouting control system according to claim 4, characterized in that, The filtering method of the Kalman filter joint model includes: Using the state prediction equation, obtain the predicted state value of the th anchor bolt at time ; Using the error covariance prediction equation, obtain the th anchor bolt's predicted error covariance matrix at time ; By combining the prediction error covariance, the observation matrix, the observation equation and the covariance of the observation noise, Get the Kalman gain; The residual is calculated. After obtaining the residual, the predicted value is updated through the state update equation to obtain the updated predicted state value. At the same time, the error covariance is updated according to the Kalman gain using the error covariance update equation.

6. The adaptive grouting control system for an anchor rod according to claim 1, wherein The method for obtaining grouting adjustment parameters includes: dividing the monitoring data into N data areas based on the anchor rod number, using an optimization algorithm to determine the target grouting amount of each anchor rod, merging the target grouting amount and the data area belonging to the anchor rod number into a data area, inputting the data area into a pre-built adaptive control model, and outputting the grouting adjustment parameters.

7. The self - adaptive grouting control system for an anchor rod according to claim 6, wherein, The method for obtaining the target grouting amount comprises: Initialize the particle swarm, where each particle represents a target grouting volume combination and has a length of N; Use the fitness function to calculate the fitness value; Update the particle positions and velocities using the position update equation and the velocity update equation, and perform iterative calculations. In each iteration, recalculate the fitness value of each particle. If the termination condition is reached, terminate the iteration. The termination conditions include: Reaching the maximum number of iterations; the change in the global best fitness is less than a preset threshold.

8. The adaptive grouting control system for an anchor rod according to claim 6, wherein The training method of the adaptive control model includes: Use all data zones as the input of the adaptive control model. The adaptive control model outputs the corresponding grouting adjustment parameters predicted for each group of data zones. Use the actual grouting adjustment parameters corresponding to each group of data zones as the prediction target, and use minimizing the sum of the second prediction accuracies of all predicted grouting adjustment parameters as the training target. Train the adaptive control model until the sum of the second prediction accuracies reaches convergence and then stop training. The adaptive control model is a support vector machine.

Images