Anchoring system prestress active regulation and control method based on surrounding rock deformation monitoring

Abstract

The invention discloses an anchoring system prestress active regulation and control method based on surrounding rock deformation monitoring, and relates to the technical field of geotechnical engineering supporting, and the method comprises the following steps: arranging various types of sensors in a surrounding rock supporting area, and collecting transverse displacement, vertical displacement, stress change and environmental parameters of surrounding rock in real time; and the data is transmitted to the central processing unit through the wireless data transmission module. By monitoring surrounding rock deformation in real time, the response speed of an anchoring system is increased, and the long-term stability of an engineering structure is ensured; the prestress is intelligently regulated and controlled, fuzzy control and a self-adaptive PID algorithm are combined, dynamic adjustment is achieved, human intervention is reduced, and the supporting efficiency is improved; the maintenance cost is reduced, the service life of an anchoring system is prolonged, manual inspection and material waste are reduced, and economic benefits are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of geotechnical engineering support, and in particular to a method for actively regulating prestress of an anchoring system based on surrounding rock deformation monitoring. Background Art

[0002] Active prestress control of the anchor system based on surrounding rock deformation monitoring involves dynamically adjusting the prestress of the anchor system (e.g., anchor rods and cables) by monitoring surrounding rock deformation in real time and combining intelligent analysis with automatic control technologies to ensure optimal support. This method utilizes multi-dimensional sensors (such as triaxial accelerometers, strain gauges, and laser displacement sensors) to collect surrounding rock deformation data and analyzes its movement trends using deep learning algorithms. When the system detects that surrounding rock deformation exceeds a set threshold, a prestress control unit (such as an electro-hydraulic loading device or a shape memory alloy preload device) automatically adjusts the prestress of the anchor system to adapt to the dynamic changes in the surrounding rock, preventing a decrease in support effectiveness due to prestress loss. Compared to traditional methods that rely on manual adjustment or passive reinforcement, this system achieves a closed-loop optimization process of real-time monitoring, intelligent analysis, and automatic control, improving support accuracy and enhancing surrounding rock stability while reducing construction and maintenance costs.

[0003] The existing technology has the following shortcomings: In the anchoring system based on surrounding rock deformation monitoring, sensors are responsible for collecting data such as displacement and stress of the surrounding rock, which serves as the key basis for regulating prestress. However, during long-term operation or in extreme environments (such as high humidity, high temperature or strong electromagnetic interference), sensors may experience drift, noise amplification or error accumulation, resulting in deviations in the collected data. If the system fails to detect and correct these errors in a timely manner, it may cause inaccurate prestress control. For example, the system mistakenly believes that the surrounding rock deformation has intensified, thereby excessively increasing the prestress, which may cause local damage to the anchor rod or rock mass, and accelerate the instability of the surrounding rock; conversely, if the surrounding rock deformation is mistakenly judged to be stable, the system may fail to compensate for the prestress loss in time, weakening the support effect, and ultimately causing large-scale surrounding rock instability or collapse. Therefore, how to ensure the reliability of sensor data and avoid misregulation during long-term operation is a hidden but high-risk technical challenge in the process of active prestress control of the anchoring system.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide an active control method for prestressing of an anchoring system based on surrounding rock deformation monitoring. By real-time monitoring of surrounding rock deformation, the response speed of the anchoring system is improved, ensuring the long-term stability of the engineering structure. Intelligent control of prestressing is adopted, combined with fuzzy control and adaptive PID algorithms, to achieve dynamic adjustment, reduce human intervention, and improve support efficiency. By reducing maintenance costs, the service life of the anchoring system is extended, manual inspections and material waste are reduced, and economic benefits are improved. Compared with traditional methods, the present invention can reduce maintenance workload by 30%-50%, increase the service life of anchor rods by more than 40%, enhance the adaptability of the support system, make it more accurately match complex geological environments, and improve the safety and stability of the project, thereby solving the problems in the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for actively controlling prestressing of an anchoring system based on surrounding rock deformation monitoring, comprising the following steps:

[0007] Various types of sensors are deployed in the surrounding rock support area to collect the lateral displacement, vertical displacement, stress changes and environmental parameters of the surrounding rock in real time, and transmit the data to the central processing unit through the wireless data transmission module;

[0008] Adopting adaptive error compensation algorithm, drift correction, noise filtering and environmental factor compensation are performed on the collected data. Using historical monitoring data and deep learning algorithm to establish a dynamic correction model, the long-term stability and high accuracy of the data are guaranteed.

[0009] By integrating real-time monitoring data with the historical deformation characteristics of the surrounding rock, a surrounding rock deformation trend model based on time series prediction is constructed. The neural network algorithm is used to determine the rate of change, direction and stability of surrounding rock deformation, and to predict the deformation trend of the surrounding rock within a certain period of time in the future.

[0010] The optimal prestress adjustment amount of the anchor system is calculated based on the deformation trend model. Combined with the feedback control mechanism, the prestress increase and decrease strategy of the anchor system is determined to ensure that the support structure adapts to the dynamic changes of the surrounding rock while avoiding miscontrol caused by data errors.

[0011] The prestressing adjustment operation is performed through the electric hydraulic loading device, which changes the preload force of the anchoring system in real time to maintain it within the set range, thereby improving the long-term stability of the anchoring system;

[0012] Combined with the surrounding rock deformation data after prestress adjustment, the control effect is evaluated, and the error compensation, deformation prediction and prestress control models are continuously optimized, so that the anchoring system can adapt to complex working conditions and continuously improve the control accuracy and stability during long-term operation.

[0013] Preferably, the active control method further includes a data redundancy and multi-source fusion correction mechanism to improve the accuracy of surrounding rock deformation monitoring, and the data redundancy correction includes the following contents;

[0014] Deploy multiple sensors of different types at the same monitoring point to collect displacement, stress, and vibration data respectively;

[0015] The weighted average method is used to calculate the comprehensive measurement value of each sensor data to minimize the measurement error;

[0016] Perform trend analysis on historical data. If the change in the current data point deviates abnormally from the historical trend, the error correction algorithm is triggered to adaptively adjust the sensor data.

[0017] Combined with the neural network model, the multi-source fusion of the measurement values of different sensors is performed, and the drift error of individual sensors is corrected based on the model training results;

[0018] A real-time data optimization method based on Kalman filtering is used to improve the stability and accuracy of surrounding rock deformation measurement.

[0019] Preferably, the active control method further adopts a hierarchical control strategy to adapt to the deformation of surrounding rocks in different areas and improve the control accuracy of the anchoring system. The hierarchical control strategy includes the following steps:

[0020] The local control layer, at the level of a single anchoring system, monitors local stress changes in real time through embedded micro-sensors and makes fine adjustments to prestress in a small area based on a fast response algorithm;

[0021] The regional control layer integrates the data of all monitoring points at the unit area level composed of multiple anchor systems, calculates the overall deformation trend in the area, and uses fuzzy control algorithms to optimize the overall stiffness of the anchor system;

[0022] The global control layer, at the entire engineering structure level, uses a deep learning prediction model to analyze the deformation trend of the surrounding rock based on long-term monitoring data and dynamically allocates the prestressing parameters in each area to optimize the long-term stability of the entire support system.

[0023] Preferably, the active control method further combines the creep characteristics of the surrounding rock to perform long-term control to compensate for the prestress attenuation caused by the creep effect, including the following steps:

[0024] Collect stress change data of the anchoring system at different time periods and establish a mathematical model of surrounding rock creep;

[0025] The exponential decay function is used to fit the prestress loss curve and the prestress compensation value at the key time point is calculated;

[0026] Dynamically adjust prestressing force by combining multi-time scale prediction methods;

[0027] When the creep rate of the surrounding rock accelerates, the prestress of the anchoring system is automatically increased to prevent excessive deformation from causing structural instability.

[0028] Preferably, the prestressing adjustment device adopts a shape memory alloy driving mechanism to achieve adaptive adjustment, and the shape memory alloy driving mechanism includes: a shape memory alloy wire or sheet installed inside the anchoring system;

[0029] The shape memory effect is triggered by electric current heating, causing the shape memory alloy to contract or expand, thereby adjusting the prestress of the anchoring system;

[0030] Adopting feedback control system and combining real-time monitoring data to adjust the heating power of shape memory alloy, it can achieve precise prestress control;

[0031] The phase transition temperature range of shape memory alloys is optimized to meet the long-term working requirements in different ambient temperatures.

[0032] Preferably, the data processing unit adopts a deep learning neural network model to improve the prediction accuracy of surrounding rock deformation, and the neural network model includes: using a long short-term memory network combined with a convolutional neural network to extract time series features and spatial deformation patterns respectively;

[0033] Adjust network hyperparameters through adaptive optimization algorithms to improve the generalization ability of the model;

[0034] Use data augmentation technology to expand the training data set and improve the model's adaptability to different geological conditions;

[0035] Combined with physics-driven modeling methods, data-driven prediction results are corrected to ensure that the calculation results meet actual engineering constraints.

[0036] Preferably, the active control method is further combined with wireless transmission technology to achieve remote monitoring and intelligent control, and the wireless transmission technology includes: using low-power wide area network technology to extend the life of the sensor;

[0037] Combined with edge computing technology, data preprocessing is performed on the sensor side to reduce the bandwidth requirements for data transmission;

[0038] Adopting a distributed storage method based on blockchain to ensure the security and non-tamperability of data.

[0039] Preferably, the active control method adopts a combination of fuzzy control and incremental PID control to improve the stability of prestress control.

[0040] Preferably, the prestress calculation method comprises the following steps:

[0041] Calculate the total deformation of the surrounding rock using the following expression: ΔL = L t -L0, where L t is the current measured displacement, L0 is the initial displacement, and ΔL is the total deformation of the surrounding rock;

[0042] Calculate the anchor rod prestress adjustment amount, the calculation expression is as follows: Among them, E s is the elastic modulus of the anchor material, σ p is the anchor rod prestress adjustment amount;

[0043] Combined with the surrounding rock creep compensation, the calculation expression is as follows: σ adj =σ p +C·exp(-λt), where σ adj is the final adjustment value of prestress, C is the creep influence coefficient, λ is the creep attenuation rate, and t is time.

[0044] Preferably, the prestress optimization calculation adopts a genetic algorithm for iterative solution, and the specific steps are as follows:

[0045] Initialize the population and calculate the expression as follows: P0={x i}={x1,x2,……,x n}, where P0 is the initial population, x i is the i-th individual, n is the total number of individuals;

[0046] Calculate the fitness function, the calculation expression is as follows:

[0047] f(x)=w1·σ p +w2·ΔL+w3·σ adj

[0048] , where f(x) is the fitness function, σ p is the prestress adjustment of the anchoring system, w1 is the weight coefficient of the prestress adjustment of the anchoring system, w2 is the weight coefficient of the total deformation of the surrounding rock ΔL, and w3 is the weight coefficient of the final adjustment value of the prestress;

[0049] The crossover and mutation operation is used for iterative optimization until the convergence condition is met. The expression is as follows: (x), where P is the population of prestressing configuration schemes, x is an individual prestressing configuration scheme, f(x) is the fitness function, and max is the maximization operator.

[0050] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0051] The present invention can achieve real-time monitoring of surrounding rock deformation, improve the response speed of the anchoring system, and ensure structural stability. In traditional anchoring support systems, the monitoring of surrounding rock deformation mainly relies on manual inspections and regular data collection. This method not only has delayed feedback, but also makes it difficult to capture subtle changes in surrounding rock deformation, resulting in the inability to follow up on prestressing adjustments in a timely manner, increasing the risk of surrounding rock instability. The present invention can collect surrounding rock deformation data in real time 24 hours a day by deploying a multidimensional sensor network in the anchoring system, such as fiber grating sensors, laser displacement sensors, strain gauges, and accelerometers, and combines remote wireless transmission technology to upload the data to a central control system in real time. This not only improves the accuracy of data collection, but also significantly enhances the early warning capability. When abnormal deformation of the surrounding rock occurs, the system can detect and trigger an early warning in the first time, reminding construction personnel to take measures. In addition, combined with deep learning algorithms and time series prediction technology, the system can identify surrounding rock deformation trends in advance and take preventive measures before structural instability occurs, thereby effectively reducing the incidence of engineering accidents. Compared with traditional monitoring methods, the present invention provides a more accurate, efficient and automated surrounding rock deformation monitoring solution, which greatly improves the long-term safety of engineering structures.

[0052] The present invention can intelligently control prestress, reduce human intervention, and improve the adaptability and support efficiency of the anchoring system. The adjustment of prestress in traditional anchoring systems mainly relies on manual experience, and usually adopts the method of "initial high prestress" or "regular tightening of anchor cables" to deal with the uncertainty of surrounding rock deformation. However, due to factors such as rock creep, stress redistribution, and environmental changes, the prestress of the anchoring system will inevitably decay during long-term operation. Relying solely on manual adjustment not only has a low adjustment frequency and is difficult to compensate for prestress loss in a timely manner, but may also cause the support system to fail due to operational errors. The present invention combines intelligent control algorithms (such as fuzzy control, adaptive PID regulation, etc.) to dynamically adjust the prestress of anchor rods or anchor cables according to real-time deformation data of the surrounding rock. When the surrounding rock undergoes rapid deformation, the system can automatically increase the prestress, enhance the support stiffness, and prevent further damage to the surrounding rock; when the surrounding rock tends to be stable, the system will automatically reduce the prestress, reduce material fatigue damage of the anchor rod, and extend the service life of the anchoring system. In addition, the present invention adopts an electric hydraulic loading device or a shape memory alloy drive mechanism, which can accurately control the adjustment amplitude and rate of the prestress, realize an unmanned fully automated control mode, enable the support system to adapt to complex and changeable geological environments, improve the overall support efficiency, and significantly reduce manual maintenance costs.

[0053] The present invention can reduce engineering maintenance costs, extend the service life of the anchoring system, and improve economic benefits. In engineering fields such as mining, tunneling, and water conservancy and hydropower dam reinforcement, the maintenance cost of traditional anchoring systems is relatively high, mainly reflected in frequent manual inspections, complex tightening and adjustment, and the need for regular replacement of anchor rods and cables due to fatigue damage. Especially in the long-term operation process, due to factors such as prestress loss and surrounding rock creep, the maintenance frequency of the support system is relatively high. Once maintenance is not timely, it may cause further deformation or even instability of the surrounding rock, resulting in high remedial costs. The intelligent anchoring system of the present invention greatly reduces the need for manual inspections and maintenance through a real-time monitoring + active control mode, making the management of the anchoring system more efficient. The system can make compensatory adjustments in advance before the prestress drops to the threshold, avoiding damage to the anchor rods caused by excessive attenuation of the prestress, thereby extending the service life of the support system. In addition, the present invention maximizes the utilization rate of anchoring materials through data-driven precise control, avoids unnecessary material waste, and thus reduces long-term engineering costs. Compared with traditional methods, this system can reduce manual maintenance workload by 30%-50% and increase the service life of anchor rods by at least 40%. While reducing construction costs, it also significantly improves the overall economic benefits of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction to the drawings required for use in the embodiments will be given below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0055] Figure 1 This is a flow chart of the method for active control of prestressing of the anchoring system based on surrounding rock deformation monitoring of the present invention. DETAILED DESCRIPTION

[0056] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0057] The present invention provides Figure 1 The method for active prestress control of the anchoring system based on surrounding rock deformation monitoring includes the following steps:

[0058] Various types of sensors are deployed in the surrounding rock support area, including triaxial accelerometers, strain gauges, laser displacement sensors, and environmental monitoring sensors. These sensors collect the lateral displacement, vertical displacement, stress changes, and environmental parameters of the surrounding rock in real time, and transmit the data to the central processing unit via a wireless data transmission module.

[0059] Adopting adaptive error compensation algorithm, drift correction, noise filtering and environmental factor compensation are performed on the collected data. Using historical monitoring data and deep learning algorithm to establish a dynamic correction model, the long-term stability and high accuracy of the data are guaranteed.

[0060] By integrating real-time monitoring data with the historical deformation characteristics of the surrounding rock, a surrounding rock deformation trend model based on time series prediction is constructed. The neural network algorithm is used to determine the rate of change, direction and stability of surrounding rock deformation, and to predict the deformation trend of the surrounding rock within a certain period of time in the future.

[0061] The optimal prestress adjustment amount of the anchor system is calculated based on the deformation trend model. Combined with the feedback control mechanism, the prestress increase and decrease strategy of the anchor system (anchor rod or anchor cable) is determined to ensure that the support structure adapts to the dynamic changes of the surrounding rock while avoiding miscontrol caused by data errors.

[0062] The prestressing adjustment operation is performed through the shape memory alloy prestressing device, which changes the prestressing force of the anchoring system (anchor rod or anchor cable) in real time to maintain it within the set range, thereby improving the long-term stability of the anchoring system;

[0063] Combined with the surrounding rock deformation data after prestress adjustment, the control effect is evaluated, and the error compensation, deformation prediction and prestress control models are continuously optimized, so that the anchoring system can adapt to complex working conditions and continuously improve the control accuracy and stability during long-term operation.

[0064] The active control method further includes data redundancy and multi-source fusion correction mechanisms to improve the accuracy of surrounding rock deformation monitoring. Data redundancy correction includes the following:

[0065] Deploy multiple different types of sensors (such as laser displacement sensors, accelerometers, and strain gauges) at the same monitoring point to collect displacement, stress, and vibration data respectively;

[0066] The weighted average method is used to calculate the comprehensive measurement value of each sensor data to minimize the measurement error;

[0067] Perform trend analysis on historical data. If the change in the current data point deviates abnormally from the historical trend, the error correction algorithm is triggered to adaptively adjust the sensor data.

[0068] Combined with the neural network model, the multi-source fusion of the measurement values of different sensors is performed, and the drift error of individual sensors is corrected based on the model training results;

[0069] A real-time data optimization method based on Kalman filtering is used to improve the stability and accuracy of surrounding rock deformation measurement.

[0070] The active control method further adopts a hierarchical control strategy to adapt to the deformation of the surrounding rock in different areas and improve the control accuracy of the anchoring system. The hierarchical control strategy includes the following steps:

[0071] The local control layer monitors local stress changes in real time at the level of a single anchoring system (anchor rod or cable) through embedded micro sensors, and fine-tunes prestressing in a small area based on a fast response algorithm;

[0072] The regional control layer integrates the data of all monitoring points at the unit area level composed of multiple anchor systems (anchor rods or anchor cables), calculates the overall deformation trend in the area, and uses fuzzy control algorithm to optimize the overall stiffness of the anchor system;

[0073] The global control layer, at the entire engineering structure level, uses a deep learning prediction model to analyze the deformation trend of the surrounding rock based on long-term monitoring data and dynamically allocates the prestressing parameters in each area to optimize the long-term stability of the entire support system.

[0074] The active control method further combines the creep characteristics of the surrounding rock to perform long-term control to compensate for the prestress attenuation caused by the creep effect. It includes the following steps:

[0075] Collect stress change data of the anchoring system at different time periods and establish a mathematical model of surrounding rock creep;

[0076] The exponential decay function is used to fit the prestress loss curve and the prestress compensation value at the key time point is calculated;

[0077] Dynamically adjust prestressing force by combining multi-time scale prediction methods (local regression for short-term prediction and recursive neural network for long-term prediction);

[0078] When the creep rate of the surrounding rock accelerates, the prestress of the anchoring system is automatically increased to prevent excessive deformation from causing structural instability.

[0079] The prestressing adjustment device adopts a shape memory alloy drive mechanism to achieve adaptive adjustment. The shape memory alloy drive mechanism includes:

[0080] Shape memory alloy wire or sheet, installed inside the anchoring system (anchor rod or anchor cable);

[0081] The shape memory effect is triggered by electric current heating, causing the shape memory alloy to contract or expand, thereby adjusting the prestress of the anchoring system;

[0082] Adopting feedback control system and combining real-time monitoring data to adjust the heating power of shape memory alloy, it can achieve precise prestress control;

[0083] The phase transition temperature range of shape memory alloys is optimized to meet the long-term working requirements in different ambient temperatures.

[0084] The data processing unit uses a deep learning neural network model to improve the accuracy of surrounding rock deformation prediction. The neural network model includes:

[0085] Long short-term memory (LSTM) network combined with convolutional neural network (CNN) is used to extract time series features and spatial deformation patterns respectively;

[0086] Adjust network hyperparameters through adaptive optimization algorithms to improve the generalization ability of the model;

[0087] Use data augmentation technology to expand the training data set and improve the model's adaptability to different geological conditions;

[0088] Combined with physics-driven modeling methods, data-driven prediction results are corrected to ensure that the calculation results meet actual engineering constraints.

[0089] Active control methods are further combined with wireless transmission technologies to achieve remote monitoring and intelligent control. Wireless transmission technologies include:

[0090] Adopting low-power wide-area network (LPWAN) technology to extend the battery life of sensors;

[0091] Combined with edge computing technology, data preprocessing is performed on the sensor side to reduce the bandwidth requirements for data transmission;

[0092] Adopting a distributed storage method based on blockchain to ensure the security and non-tamperability of data.

[0093] The active control method adopts a combination of fuzzy control and incremental PID control to improve the stability of prestress control.

[0094] The prestress calculation method includes the following steps:

[0095] Calculate the total deformation of the surrounding rock using the following expression: ΔL = L t -L0, where L t is the current measured displacement, L0 is the initial displacement, and ΔL is the total deformation of the surrounding rock;

[0096] Calculate the anchor rod prestress adjustment amount, the calculation expression is as follows: Among them, E s is the elastic modulus of the anchor material, σ p is the anchor rod prestress adjustment amount;

[0097] Combined with the surrounding rock creep compensation, the calculation expression is as follows: σ adj =σ p +C·exp(-λt), where σ adj is the final adjustment value of prestress, C is the creep influence coefficient, λ is the creep attenuation rate, and t is time.

[0098] The prestress optimization calculation adopts genetic algorithm for iterative solution. The specific steps are as follows:

[0099] Initialize the population and calculate the expression as follows: P0={x i}={x1,x2,……,x n}, where P0 is the initial population, representing the candidate solution set at the beginning of the genetic algorithm. Each solution is a set of possible prestress parameter configurations, x i is the i-th individual, representing a specific prestressing parameter configuration, which may include different anchor prestressing levels, anchor cable layout schemes, etc., and n is the total number of individuals;

[0100] Calculate the fitness function, the calculation expression is as follows:

[0101] f(x)=w1·σ p +w2·ΔL+w3·σ adj

[0102] , where f(x) is the fitness function, σ p is the prestress adjustment of the anchoring system (anchor rod or anchor cable), w1 is the weight coefficient of the prestress adjustment of the anchoring system (anchor rod or anchor cable), w2 is the weight coefficient of the total deformation of the surrounding rock ΔL, and w3 is the weight coefficient of the final prestress adjustment value;

[0103] The crossover and mutation operation is used for iterative optimization until the convergence condition is met. The expression is as follows: (x), where P is the population of prestressing configuration schemes, x is the individual prestressing configuration scheme, f(x) is the fitness function, which is used to measure the quality of each prestressing adjustment scheme x. The larger the value, the more the scheme meets the optimization goal. max is the maximization operator, which means that the goal is to find the prestressing configuration scheme that maximizes f(x), that is, the optimal prestressing adjustment method of the anchoring system.

[0104] It means to find the optimal solution that maximizes the fitness function f(x) among all possible prestressing configuration schemes P. The fitness function f(x) is calculated by weighting multiple factors, including the prestressing adjustment amount σ p , the total deformation of the surrounding rock ΔL and the final prestress value after creep compensation σ adj, where weight coefficients w1, w2, w3, and w4 are set based on actual working conditions. Through genetic algorithm optimization, the system continuously selects, crosses, and mutates within population P, iteratively searching for the optimal prestressing adjustment strategy. This allows the anchor system to consistently maintain optimal support in dynamic surrounding rock environments, thereby improving stability and reducing maintenance costs.

[0105] Implementation method 1: During mining, tunnels are important passages for miners and equipment, and are also key safety support areas during mining production. However, due to the complex geological conditions of underground ore bodies, the surrounding rock of tunnels is usually in a high-stress environment. Affected by factors such as mining, ground stress release, and groundwater infiltration, the surrounding rock may undergo varying degrees of deformation, including convergence deformation, shear deformation, and expansion deformation. Traditional anchor support methods can provide a certain degree of stability during initial construction, but over time, due to factors such as continuous deformation of the surrounding rock, loss of prestress, and aging of materials, the support effect gradually decreases. In severe cases, it may cause the deformation of the tunnel to intensify or even become unstable, endangering personnel safety and the continuity of mine production. Therefore, how to improve the long-term stability of the tunnel support system, reduce prestress loss, and improve the support effect has become a key technical problem in the field of mining engineering.

[0106] The proposed method for actively controlling the prestressing force of the anchor system based on surrounding rock deformation monitoring utilizes multi-dimensional sensors deployed within the tunnel support area. By monitoring surrounding rock deformation in real time, analyzing its changing trends with intelligent algorithms, and actively controlling the prestressing force of the anchor rods, the system is ensured to maintain optimal working conditions. This method overcomes the limitations of traditional support methods, which rely on static initial prestressing force, and instead combines intelligent monitoring with dynamic control to achieve precise support for the tunnel surrounding rock.

[0107] 1. Construction of monitoring system

[0108] The present invention first deploys a multi-dimensional high-precision sensor network within the tunnel support area to collect surrounding rock deformation data in real time. These sensors include:

[0109] Laser displacement sensor: used to measure the lateral and vertical displacement of surrounding rock with an accuracy of up to millimeter level, which can accurately reflect the deformation trend of surrounding rock;

[0110] Accelerometer: used to monitor the micro-vibration of the surrounding rock and determine whether the surrounding rock has a potential instability trend;

[0111] Strain gauge: installed on the anchor rod to monitor the stress state of the anchor rod in real time and determine the prestress changes of the anchoring system;

[0112] Wireless data acquisition module: used to wirelessly transmit the collected data to the central control system to achieve remote monitoring and intelligent analysis.

[0113] These sensors communicate with the central control system through wireless networks (such as low-power wide area networks LPWAN or Wi-Fi) to ensure the real-time and stability of data.

[0114] 2. Data analysis and prestress control

[0115] The collected surrounding rock deformation data is transmitted to the central control system, which uses a deep learning algorithm to analyze the surrounding rock deformation trend and automatically adjusts the prestressing level of the anchor bolts based on the calculation results. The control process is as follows:

[0116] Surrounding rock deformation trend analysis: Deep learning algorithms model the data collected by sensors, identify the deformation pattern of the surrounding rock, and predict future deformation trends.

[0117] Intelligent judgment of prestressing demand: Calculate the current required prestressing adjustment amount based on the surrounding rock deformation rate, deformation direction and anchor stress state.

[0118] Automatic adjustment of prestressing force:

[0119] When the surrounding rock undergoes rapid deformation: the system automatically increases the prestress, improves the support stiffness of the anchor rod, and prevents further damage to the surrounding rock.

[0120] After the surrounding rock becomes stable: the system appropriately reduces the prestress to reduce material fatigue damage of the anchor rod and extend the service life of the support system.

[0121] Real-time feedback mechanism: The adjusted prestress data is recorded in real time and compared with the data collected by the sensor to ensure that the adjustment effect meets the expectations.

[0122] This intelligent control strategy breaks the limitations of traditional reliance on manual experience for prestress adjustment, improves the accuracy and real-time performance of regulation, and enables the support system to adapt to the continuous deformation of the surrounding rock.

[0123] 3. Prestressed control device

[0124] In order to achieve active regulation of prestress, the present invention adopts an electric hydraulic loading device or a shape memory alloy drive mechanism. These two devices are suitable for different construction environments:

[0125] Electric hydraulic loading device: The tension of the anchor bolt is controlled by the hydraulic system, which can quickly and accurately adjust the prestressing force and is suitable for larger-scale mine tunnels.

[0126] Shape memory alloy drive mechanism: Utilizing the temperature response characteristics of shape memory alloy, the anchor rod automatically adjusts the prestress under different temperature conditions. It is suitable for deep buried tunnels where it is difficult to lay hydraulic systems.

[0127] Both devices can automatically adjust the prestress of the anchor rod according to the feedback from the monitoring system, so that the tunnel support system is always in the best condition.

[0128] 4. Advantages of this method

[0129] Compared with traditional tunnel support methods, the present invention has the following advantages:

[0130] Real-time monitoring improves the response speed of the support system: Through real-time monitoring of the sensor network, surrounding rock deformation data can be quickly obtained, improving the anchoring system's ability to perceive changes in surrounding rock conditions.

[0131] Intelligent control reduces human intervention: Deep learning and adaptive control algorithms are used to achieve intelligent adjustment of prestressing, avoiding the errors caused by traditional reliance on manual experience and improving the accuracy of prestressing control.

[0132] Improve support efficiency and reduce maintenance costs: Traditional anchor support systems require regular manual inspection and maintenance, while this system can automatically detect prestress loss and compensate in real time, reducing manual intervention and improving construction efficiency.

[0133] Reduce material fatigue damage and extend the service life of the anchoring system: Traditional methods often use high initial prestress to compensate for the later prestress loss, but this can easily accelerate the fatigue damage of the anchor material. This method can dynamically adjust the prestress, reduce the excessive load of the anchor, and improve the long-term stability of the support system.

[0134] Adaptability to complex tunnel surrounding rock conditions: Different rock formations have different prestressing requirements. This method can perform personalized regulation based on real-time monitoring data, enabling the support system to adapt to different types of surrounding rock environments and improve its stability and safety.

[0135] In summary, the active prestress control method of the anchoring system based on surrounding rock deformation monitoring of the present invention successfully solves the problem of prestress attenuation in mine tunnel support through intelligent monitoring, deep learning analysis and active prestress control, improves the long-term stability of the support system, and has broad engineering application prospects.

[0136] Implementation method 2: Tunnel excavation projects are an important part of modern infrastructure construction and are widely used in railways, highways, urban subways, water conservancy projects, mining and other fields. However, during the tunnel excavation process, the surrounding rock may undergo large-scale non-uniform deformation after being disturbed by excavation. The traditional anchoring system is difficult to adapt to this complex change and is prone to the risk of local instability or surrounding rock collapse. Due to the large uncertainty in the physical and mechanical properties of the surrounding rock during tunnel construction, its deformation characteristics are often difficult to predict. Traditional passive support methods usually rely on construction experience and the setting of initial support strength, and cannot actively adjust according to the real-time deformation state of the surrounding rock. This method has a delayed response when facing sudden surrounding rock deformation, which may lead to insufficient or excessive loss of anchor prestress, thereby weakening the support effect and ultimately increasing construction safety risks and maintenance costs.

[0137] The anchoring system of this invention utilizes intelligent monitoring and active control technology. By deploying monitoring devices within the tunnel wall, it collects high-frequency data on surrounding rock deformation and dynamically adjusts the anchor bolt prestress using a fuzzy control algorithm and an adaptive PID control strategy. This method accurately senses the deformation trends of the surrounding rock and, based on an intelligent control algorithm, proactively adjusts the support system to adapt to dynamic changes in the surrounding rock, improving construction safety while reducing project delays and additional maintenance costs.

[0138] 1. Construction of monitoring system

[0139] During tunnel excavation, the present invention deploys a high-precision, multi-dimensional monitoring sensor network inside the tunnel wall to obtain the dynamic deformation of the surrounding rock in real time. The monitoring system mainly includes:

[0140] Fiber Bragg grating sensor: used to monitor the strain changes inside the surrounding rock and accurately evaluate the stress state of the surrounding rock.

[0141] Laser displacement sensor: installed on the tunnel wall surface, used to measure the convergence deformation of the surrounding rock and promptly identify possible unstable areas.

[0142] Accelerometer: used to monitor the vibration frequency and small disturbances of the surrounding rock, and to determine whether there are signs of surrounding rock instability.

[0143] Strain gauge: Installed inside the anchor rod or cable, it monitors the stress state of the anchoring system in real time and evaluates changes in prestress.

[0144] Wireless data acquisition terminal: aggregates data from various sensors in real time and sends it to the central control system through a wireless transmission module to achieve remote monitoring and data analysis.

[0145] These monitoring devices can achieve real-time communication via low-power wide area networks (LPWAN) or 5G networks, ensuring stable and low-latency data transmission. Furthermore, the system can be integrated with the Internet of Things (IoT) architecture to build a cloud-based data analysis platform, enabling engineers to remotely monitor tunnel surrounding rock deformation and promptly implement necessary support adjustments.

[0146] 2. Data analysis and proactive regulation

[0147] The intelligent control system of the present invention combines fuzzy control algorithms with adaptive PID adjustment strategies to ensure the accuracy and stability of prestress adjustment. Specifically, the control system includes the following core functions:

[0148] Analysis of surrounding rock deformation trend

[0149] The surrounding rock deformation data collected by the monitoring system is first filtered and processed for outliers to remove noise. Deep learning algorithms are then used to analyze deformation trends. For example, if the surrounding rock deformation rate increases, the vibration frequency is abnormal, or the anchor stress drops sharply, the system will determine that the surrounding rock may be at risk of instability and enter active control mode.

[0150] Intelligent calculation of prestress adjustment scheme

[0151] Using a fuzzy control algorithm, the system calculates the optimal prestressing adjustment plan based on surrounding rock deformation trends, anchor bolt stress states, and historical data. For example, if a region of surrounding rock experiences rapid deformation, the system automatically determines that the anchor bolt support strength in that area needs to be increased and sends adjustment instructions to the prestressing device.

[0152] Automatic adjustment of prestress

[0153] After calculating the optimal adjustment solution, the system will dynamically adjust the prestress of the anchor rod through an electric hydraulic loading device or a shape memory alloy drive mechanism:

[0154] When the deformation rate of the surrounding rock increases or abnormal deformation occurs in the stress concentration area, the system automatically increases the prestress of the anchor rods in the area to improve the local support strength to prevent deformation expansion.

[0155] When the deformation of the surrounding rock slows down or tends to be stable, the system appropriately reduces the prestress to prevent rock damage caused by excessive reinforcement and ensure the long-term stability of the support system.

[0156] Real-time feedback and closed-loop control

[0157] The effect of prestressing adjustment is recorded in real time by the monitoring system and compared with the data before adjustment. If the system detects that the adjustment effect does not meet the expectations, it will automatically correct the adjustment parameters and perform secondary optimization to ensure the prestressing adjustment is optimal.

[0158] 3. Prestressed control device

[0159] The present invention uses an electric hydraulic loading device or a shape memory alloy drive mechanism to achieve active regulation of prestress:

[0160] Electric hydraulic loading device: It adjusts the tension of the anchor rod through the hydraulic system. It is suitable for large tunnel projects and can provide a large prestress adjustment range.

[0161] Shape memory alloy drive mechanism: Utilizing the temperature response characteristics of shape memory alloy, the anchor rod automatically adjusts the prestress under different temperature conditions. It is suitable for deep tunnel sections with greater construction difficulty or high temperature and high humidity environments.

[0162] Both control devices can automatically adjust according to the surrounding rock deformation monitoring data to ensure that the tunnel support system is always in the best working condition.

[0163] 4. Advantages of this method

[0164] Compared with traditional tunnel support methods, the intelligent control anchoring system of the present invention has the following advantages:

[0165] Real-time monitoring to improve construction safety

[0166] Traditional methods rely on manual monitoring and have delayed feedback, while the intelligent monitoring system of the present invention can achieve high-frequency data collection and combine it with intelligent analysis to ensure the stability of the support system during tunnel excavation.

[0167] Dynamic control to improve support accuracy

[0168] The traditional anchoring system uses static prestressing, while this method can make dynamic adjustments according to the actual deformation of the surrounding rock, making the support system more flexible and improving the support effect.

[0169] Reduce maintenance costs and improve construction efficiency

[0170] Traditional methods require regular anchor maintenance, but the present invention can automatically detect prestress loss and perform real-time compensation, reducing manual inspection costs and improving construction efficiency.

[0171] Adapt to complex geological conditions

[0172] The present invention adopts an intelligent control strategy, which can adapt to different rock conditions and realize personalized prestressing control. It is particularly suitable for complex tunnel geological environments such as soft rock, high ground stress and fault zones.

[0173] In summary, the intelligent monitoring and active control technology of the present invention successfully solves the shortcomings of traditional tunnel support methods, improves the long-term stability of the support system, and reduces construction risks, and has broad engineering application prospects.

[0174] Implementation 3: Application in water conservancy and hydropower dam reinforcement projects (detailed explanation)

[0175] 1. Background and Problems

[0176] In water conservancy and hydropower projects, the stability of the dam body and its surrounding rock mass is crucial to project safety. Dams are usually subjected to long-term water pressure and are also affected by environmental factors such as rock creep, earthquakes, temperature changes, and rainfall infiltration. These factors may cause long-term deformation, stress concentration, and even crack expansion in the dam body's surrounding rock. Without effective monitoring and regulation, the stability of the dam body may gradually decline, affecting the safe operation of the dam and even bringing the risk of dam failure. Traditional anchor support methods mainly rely on initial prestressed design, but due to prestress loss and surrounding rock creep effects, the support effect will gradually decrease over time. In addition, traditional dam reinforcement mainly relies on regular manual inspections, which cannot achieve real-time monitoring and dynamic adjustments. It is difficult to detect and respond to small deformations and potential risks of the dam body in a timely manner, resulting in high subsequent maintenance costs and a delayed support effect.

[0177] To address the above issues, the present invention's active control anchoring system based on surrounding rock deformation monitoring deploys high-precision monitoring sensors inside the dam body and surrounding rock formations. By real-time monitoring of the dam body's stress state, surrounding rock deformation, and potential crack expansion trends, combined with deep learning algorithms to analyze long-term deformation patterns, it achieves intelligent control of prestress. When abnormal deformation or prestress attenuation is detected, the system automatically adjusts the tension of the anchor cable to improve support capacity, thereby ensuring the long-term stability of the dam body. In addition, the system has remote monitoring and intelligent alarm functions, which can provide early warnings before abnormal situations occur and adjust the support structure in advance, effectively reducing engineering maintenance risks and improving the durability and safety of the dam body.

[0178] 2. Construction of monitoring system

[0179] To ensure the long-term stability of the dam, the intelligent anchoring system of the present invention deploys a high-precision multi-dimensional sensor network within the dam and its surrounding rock formations. The system is primarily composed of the following core sensors:

[0180] Fiber Bragg grating sensor: Installed inside the concrete of the dam and at the interface between the rock mass, it can monitor the internal stress distribution of the dam, crack expansion and the stress state of the anchoring system over a long period of time. It has high accuracy and is suitable for long-term stable monitoring.

[0181] Laser displacement sensor: deployed on the upstream and downstream sides of the dam body, used to measure the overall deformation trend of the dam body and ensure the accuracy of monitoring data.

[0182] Osmometers and groundwater monitoring sensors: used to monitor the seepage pressure and water level changes of the dam foundation rock in real time, determine whether the dam structure is affected by water erosion, and adjust the prestress in a timely manner.

[0183] Strain gauge: Installed inside the anchor cable, it monitors the stress changes in the anchoring system, promptly determines whether the prestress is attenuating, and performs prestress compensation in combination with the intelligent control system.

[0184] Wireless data acquisition terminal: used to aggregate all sensor data and transmit the data in real time to the remote monitoring center via wireless networks (such as LoRa, NB-IoT or 5G), ensuring real-time monitoring and remote control of the dam.

[0185] These sensors can realize high-frequency collection of deformation data of the dam's surrounding rock, and through data fusion and intelligent analysis systems, improve monitoring accuracy and reliability, ensuring the long-term safe operation of the dam.

[0186] 3. Data analysis and intelligent control

[0187] The intelligent control system of the present invention adopts deep learning algorithms and intelligent control strategies to ensure the accuracy and stability of prestress adjustment, and mainly includes the following steps:

[0188] Analysis of surrounding rock deformation trend

[0189] The surrounding rock deformation data collected by the monitoring system are filtered and cleaned to remove noise interference.

[0190] Using long-term monitoring data, a dam deformation model is established to analyze the creep trend, stress distribution and crack propagation pattern of the surrounding rock.

[0191] Use neural networks to predict future deformation trends and detect potential safety hazards in advance.

[0192] Intelligent calculation of prestress adjustment scheme

[0193] Combining real-time monitoring data with historical deformation records of the dam body, the stress changes and degree of prestress loss in the current area are calculated.

[0194] Adaptive control algorithm is used to determine the prestress range that needs to be increased or decreased, and adjustment instructions are sent to the prestress control device.

[0195] Automatic adjustment of prestress

[0196] When the local surrounding rock deformation of the dam exceeds the standard or cracks tend to expand, the system automatically increases the prestress of the anchor cable, improves the support stiffness, and prevents further damage.

[0197] When the surrounding rock tends to be stable, the system appropriately reduces the prestress to reduce fatigue damage to the anchor cable material and ensure long-term safety.

[0198] The data after prestressing adjustment will be recorded in real time and compared with the data before adjustment to optimize the adjustment strategy and ensure the long-term stability of the dam.

[0199] 4. Prestressed control device

[0200] In order to achieve active regulation of prestress, the present invention adopts a hydraulic loading device or a shape memory alloy drive mechanism:

[0201] Hydraulic loading device: Suitable for large hydropower dams. It controls the tension of the anchor cables through a hydraulic pump to achieve fast and accurate prestress adjustment to ensure the stability of the dam.

[0202] Shape memory alloy drive mechanism: suitable for areas deep inside the dam body or difficult to maintain. It uses the temperature response characteristics of shape memory alloy to enable the anchor cable to automatically adjust the prestress under different environmental conditions without manual intervention.

[0203] Both devices can be used in conjunction with intelligent control systems to ensure that the prestressing force can dynamically adapt to the deformation trend of the dam body.

[0204] 5. Advantages of this method

[0205] Compared with traditional dam reinforcement methods, the intelligent anchoring system of the present invention has the following advantages:

[0206] Real-time monitoring to improve dam safety

[0207] Traditional dam monitoring methods rely on manual inspections, which have long cycles and cannot reflect the deformation of the dam in real time. The intelligent monitoring system of the present invention can monitor 24 hours a day to improve safety.

[0208] Intelligent control to reduce manual intervention

[0209] Traditional reinforcement methods cannot actively adjust prestressing. This method uses a deep learning algorithm to intelligently calculate and adjust the tension of the anchor cables to keep the dam body in an optimally stable state.

[0210] Reduce maintenance costs and improve engineering efficiency

[0211] Traditional dam reinforcement projects require regular replacement of anchor cables or manual tightening, but the system of the present invention can automatically detect prestress loss and perform dynamic compensation, significantly reducing manual maintenance costs.

[0212] Adapt to complex geological environments

[0213] The system can adapt to complex environments such as soft rock, high stress, and high permeability, and is particularly suitable for large-scale hydropower projects with high dams, deep reservoirs, and earthquake-prone areas.

[0214] In summary, the active control anchoring system based on surrounding rock deformation monitoring of the present invention successfully solves the problem of long-term reinforcement and maintenance of water conservancy and hydropower dams, improves the long-term stability of the dam body, and reduces safety hazards, and has broad engineering application prospects.

[0215] The present invention can achieve real-time monitoring of surrounding rock deformation, improve the response speed of the anchoring system, and ensure structural stability. In traditional anchoring support systems, the monitoring of surrounding rock deformation mainly relies on manual inspections and regular data collection. This method not only has delayed feedback, but also makes it difficult to capture subtle changes in surrounding rock deformation, resulting in the inability to follow up on prestressing adjustments in a timely manner, increasing the risk of surrounding rock instability. The present invention can collect surrounding rock deformation data in real time 24 hours a day by deploying a multidimensional sensor network in the anchoring system, such as fiber grating sensors, laser displacement sensors, strain gauges, and accelerometers, and combines remote wireless transmission technology to upload the data to a central control system in real time. This not only improves the accuracy of data collection, but also significantly enhances the early warning capability. When abnormal deformation of the surrounding rock occurs, the system can detect and trigger an early warning in the first time, reminding construction personnel to take measures. In addition, combined with deep learning algorithms and time series prediction technology, the system can identify surrounding rock deformation trends in advance and take preventive measures before structural instability occurs, thereby effectively reducing the incidence of engineering accidents. Compared with traditional monitoring methods, the present invention provides a more accurate, efficient and automated surrounding rock deformation monitoring solution, which greatly improves the long-term safety of engineering structures.

[0216] The present invention can intelligently control prestress, reduce human intervention, and improve the adaptability and support efficiency of the anchoring system. The adjustment of prestress in traditional anchoring systems mainly relies on manual experience, and usually adopts the method of "initial high prestress" or "regular tightening of anchor cables" to deal with the uncertainty of surrounding rock deformation. However, due to factors such as rock creep, stress redistribution, and environmental changes, the prestress of the anchoring system will inevitably decay during long-term operation. Relying solely on manual adjustment not only has a low adjustment frequency and is difficult to compensate for prestress loss in a timely manner, but may also cause the support system to fail due to operational errors. The present invention combines intelligent control algorithms (such as fuzzy control, adaptive PID regulation, etc.) to dynamically adjust the prestress of anchor rods or anchor cables according to real-time deformation data of the surrounding rock. When the surrounding rock undergoes rapid deformation, the system can automatically increase the prestress, enhance the support stiffness, and prevent further damage to the surrounding rock; when the surrounding rock tends to be stable, the system will automatically reduce the prestress, reduce material fatigue damage of the anchor rod, and extend the service life of the anchoring system. In addition, the present invention adopts an electric hydraulic loading device or a shape memory alloy drive mechanism, which can accurately control the adjustment amplitude and rate of the prestress, realize an unmanned fully automated control mode, enable the support system to adapt to complex and changeable geological environments, improve the overall support efficiency, and significantly reduce manual maintenance costs.

[0217] The present invention can reduce engineering maintenance costs, extend the service life of the anchoring system, and improve economic benefits. In engineering fields such as mining, tunneling, and water conservancy and hydropower dam reinforcement, the maintenance cost of traditional anchoring systems is relatively high, mainly reflected in frequent manual inspections, complex tightening and adjustment, and the need for regular replacement of anchor rods and cables due to fatigue damage. Especially in the long-term operation process, due to factors such as prestress loss and surrounding rock creep, the maintenance frequency of the support system is relatively high. Once maintenance is not timely, it may cause further deformation or even instability of the surrounding rock, resulting in high remedial costs. The intelligent anchoring system of the present invention greatly reduces the need for manual inspections and maintenance through a real-time monitoring + active control mode, making the management of the anchoring system more efficient. The system can make compensatory adjustments in advance before the prestress drops to the threshold, avoiding damage to the anchor rods caused by excessive attenuation of the prestress, thereby extending the service life of the support system. In addition, the present invention maximizes the utilization rate of anchoring materials through data-driven precise control, avoids unnecessary material waste, and thus reduces long-term engineering costs. Compared with traditional methods, this system can reduce manual maintenance workload by 30%-50% and increase the service life of anchor rods by at least 40%. While reducing construction costs, it also significantly improves the overall economic benefits of the project.

[0218] 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.

[0219] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

[0220] It should be noted that, in this document, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0221] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0222] Those skilled in the art will appreciate that the units 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.

[0223] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0224] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0225] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0226] 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.

[0227] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. An active control method for prestressing of anchoring system based on surrounding rock deformation monitoring, characterized in that: The following steps are involved: Various types of sensors are deployed in the surrounding rock support area to collect the lateral displacement, vertical displacement, stress changes and environmental parameters of the surrounding rock in real time, and transmit the data to the central processing unit through the wireless data transmission module; Adopting adaptive error compensation algorithm, drift correction, noise filtering and environmental factor compensation are performed on the collected data. Using historical monitoring data and deep learning algorithm to establish a dynamic correction model, the long-term stability and high accuracy of the data are guaranteed. By integrating real-time monitoring data with the historical deformation characteristics of the surrounding rock, a surrounding rock deformation trend model based on time series prediction is constructed. The neural network algorithm is used to determine the rate of change, direction and stability of surrounding rock deformation, and to predict the deformation trend of the surrounding rock within a certain period of time in the future. The optimal prestress adjustment amount of the anchor system is calculated based on the deformation trend model. Combined with the feedback control mechanism, the prestress increase and decrease strategy of the anchor system is determined to ensure that the support structure adapts to the dynamic changes of the surrounding rock while avoiding miscontrol caused by data errors. The prestressing adjustment operation is performed through the electric hydraulic loading device, which changes the preload force of the anchoring system in real time to maintain it within the set range, thereby improving the long-term stability of the anchoring system; Combined with the surrounding rock deformation data after prestress adjustment, the control effect is evaluated, and the error compensation, deformation prediction and prestress control models are continuously optimized, so that the anchoring system can adapt to complex working conditions and continuously improve the control accuracy and stability during long-term operation.

2. The method for active prestress control of anchoring system based on surrounding rock deformation monitoring according to claim 1 is characterized in that: The active control method further includes data redundancy and multi-source fusion correction mechanisms to improve the accuracy of surrounding rock deformation monitoring. Data redundancy correction includes the following: Deploy multiple sensors of different types at the same monitoring point to collect displacement, stress, and vibration data respectively; The weighted average method is used to calculate the comprehensive measurement value of each sensor data to minimize the measurement error; Perform trend analysis on historical data. If the change in the current data point deviates abnormally from the historical trend, the error correction algorithm is triggered to adaptively adjust the sensor data. Combined with the neural network model, the multi-source fusion of the measurement values of different sensors is performed, and the drift error of individual sensors is corrected based on the model training results; A real-time data optimization method based on Kalman filtering is used to improve the stability and accuracy of surrounding rock deformation measurement.

3. The method for active prestress control of anchoring system based on surrounding rock deformation monitoring according to claim 1 is characterized in that: The active control method further adopts a hierarchical control strategy to adapt to the deformation of the surrounding rock in different areas and improve the control accuracy of the anchoring system. The hierarchical control strategy includes the following steps: The local control layer, at the level of a single anchoring system, monitors local stress changes in real time through embedded micro-sensors and makes fine adjustments to prestress in a small area based on a fast response algorithm; The regional control layer integrates the data of all monitoring points at the unit area level composed of multiple anchor systems, calculates the overall deformation trend in the area, and uses fuzzy control algorithms to optimize the overall stiffness of the anchor system; The global control layer, at the entire engineering structure level, uses a deep learning prediction model to analyze the deformation trend of the surrounding rock based on long-term monitoring data and dynamically allocates the prestressing parameters in each area to optimize the long-term stability of the entire support system.

4. The method for active prestress control of anchoring system based on surrounding rock deformation monitoring according to claim 1 is characterized in that: The active control method further combines the creep characteristics of the surrounding rock to perform long-term control to compensate for the prestress attenuation caused by the creep effect. It includes the following steps: Collect stress change data of the anchoring system at different time periods and establish a mathematical model of surrounding rock creep; The exponential decay function is used to fit the prestress loss curve and the prestress compensation value at the key time point is calculated; Dynamically adjust prestressing force by combining multi-time scale prediction methods; When the creep rate of the surrounding rock accelerates, the prestress of the anchoring system is automatically increased to prevent excessive deformation from causing structural instability.

5. The method for active prestress control of anchoring system based on surrounding rock deformation monitoring according to claim 1 is characterized in that: The prestressing adjustment device adopts a shape memory alloy driving mechanism to achieve adaptive adjustment. The shape memory alloy driving mechanism includes: a shape memory alloy wire or sheet installed inside the anchoring system; The shape memory effect is triggered by electric current heating, causing the shape memory alloy to contract or expand, thereby adjusting the prestress of the anchoring system; Adopting feedback control system and combining real-time monitoring data to adjust the heating power of shape memory alloy, it can achieve precise prestress control; The phase transition temperature range of shape memory alloys is optimized to meet the long-term working requirements in different ambient temperatures.

6. The method for active prestress control of anchoring system based on surrounding rock deformation monitoring according to claim 1 is characterized in that: The data processing unit uses a deep learning neural network model to improve the accuracy of surrounding rock deformation prediction. The neural network model includes: using a long short-term memory network combined with a convolutional neural network to extract time series features and spatial deformation patterns respectively; Adjust network hyperparameters through adaptive optimization algorithms to improve the generalization ability of the model; Use data augmentation technology to expand the training data set and improve the model's adaptability to different geological conditions; Combined with physics-driven modeling methods, data-driven prediction results are corrected to ensure that the calculation results meet actual engineering constraints.

7. The method for active prestress control of anchoring system based on surrounding rock deformation monitoring according to claim 1 is characterized in that: Active control methods are further combined with wireless transmission technology to achieve remote monitoring and intelligent control. Wireless transmission technologies include: using low-power wide area network technology to extend the life of sensors; Combined with edge computing technology, data preprocessing is performed on the sensor side to reduce the bandwidth requirements for data transmission; Adopting a distributed storage method based on blockchain to ensure the security and non-tamperability of data.

8. The method for active prestress control of an anchoring system based on surrounding rock deformation monitoring according to claim 1 is characterized in that: The active control method adopts a combination of fuzzy control and incremental PID control to improve the stability of prestress control.

9. The method for active prestress control of anchoring system based on surrounding rock deformation monitoring according to claim 1 is characterized in that: The prestress calculation method includes the following steps: Calculate the total deformation of the surrounding rock using the following expression: ΔL = L t -L0, where L t is the current measured displacement, L0 is the initial displacement, and ΔL is the total deformation of the surrounding rock; Calculate the anchor rod prestress adjustment amount, the calculation expression is as follows: Among them, E s is the elastic modulus of the anchor material, σ p is the anchor rod prestress adjustment amount; Combined with the surrounding rock creep compensation, the calculation expression is as follows: σ adj =σ p +C·exp(-λt), where σ adj is the final adjustment value of prestress, C is the creep influence coefficient, λ is the creep attenuation rate, and t is time.

10. The method for active prestress control of an anchoring system based on surrounding rock deformation monitoring according to claim 1, characterized in that: The prestress optimization calculation adopts genetic algorithm for iterative solution. The specific steps are as follows: Initialize the population and calculate the expression as follows: P0={x i }={x1,x2,……,x n }, where P0 is the initial population, x i is the i-th individual, n is the total number of individuals; Calculate the fitness function, the calculation expression is as follows: f(x)=w1·σ p +w2·ΔL+w3·σ adj Where f(x) is the fitness function, σ p is the prestress adjustment of the anchoring system, w1 is the weight coefficient of the prestress adjustment of the anchoring system, w2 is the weight coefficient of the total deformation of the surrounding rock ΔL, and w3 is the weight coefficient of the final adjustment value of the prestress; The crossover and mutation operation is used for iterative optimization until the convergence condition is met. The expression is as follows: (x), where P is the population of prestressing configuration schemes, x is an individual prestressing configuration scheme, f(x) is the fitness function, and max is the maximization operator.

Images