Automatic speed regulation and grouting regulation system for deep mixing pile construction in reclamation area

Abstract

The present invention relates to an automatic speed regulation and grouting regulation system for construction of a deep mixing pile in a reclamation area, the main steps comprising: first, configuring and installing a multi-modal sensing system (S101) to monitor key parameters, torque, energy consumption, grouting pressure and stratum permeability of a construction site in real time; constructing a data acquisition and fusion module (S102), integrating multi-sensor data, and forming real-time mapping of stratum-construction parameters; establishing a relation model of formation input and formation response through an extended Kalman filter (EKF) and predictive control (MPC) algorithm (S103), and intelligently evaluating formation compactness and grouting quality; on the basis of a feedback closed-loop regulation and control system (S104), the stirring speed, the grouting amount and the construction pressure are adaptively adjusted in real time, and precise control is achieved; through construction data storage and self-learning optimization (S105), the system records all construction data, and through a deep reinforcement learning optimization control algorithm, the long-term construction precision is improved.

Description

Technical Field

[0001] The present invention relates to the construction technology of deep mixing piles, and particularly to an automatic speed regulation and grouting adjustment system for the construction of deep mixing piles in reclamation areas. Background Art

[0002] Currently, in the construction of deep mixing piles in reclamation areas and other complex strata, the construction environment is often full of uncertainties and challenges. Due to the non-uniformity of the formation density, there are a large number of variables during the construction process, making it difficult to ensure the construction quality of the mixing piles. Traditional construction methods for deep mixing piles usually rely on manual experience for operation, and construction parameters such as mixing speed, feeding speed, and grouting quality often rely on manual adjustment. This method not only makes it difficult to achieve precise control but also is limited by human factors, easily leading to low construction efficiency, serious material waste, and unstable pile foundation quality. Especially in complex geological conditions, it is difficult for traditional methods to cope with the impact brought by formation changes.

[0003] In addition, traditional construction technologies are mostly based on fixed construction parameters, ignoring real-time adjustment and feedback during the construction process, making it impossible to optimize construction parameters in real-time according to formation characteristics during the construction process, resulting in uneven construction quality and low efficiency. These problems seriously affect the pile foundation construction quality in reclamation projects and other complex geological areas, increasing project costs and prolonging the construction period.

[0004] Therefore, how to achieve real-time monitoring and automatic adjustment of the construction process under complex formation conditions has become the key to improving construction quality and efficiency. In response to this problem, it is particularly important to develop an intelligent construction control system. This system can detect the density, permeability, and other key parameters of the formation in real-time and dynamically adjust construction parameters such as mixing speed and grouting volume based on real-time data, thereby ensuring precise control of the construction process and reducing human operation errors.

[0005] Based on the above needs, the present invention proposes an automatic speed regulation and grouting adjustment system for the construction of deep mixing piles. Through real-time data monitoring and intelligent control algorithms, the system can automatically optimize construction parameters according to the construction environment and formation characteristics, significantly improving construction efficiency, reducing material waste, and ensuring stable pile foundation quality. Compared with traditional methods, the system of the present invention not only improves the construction accuracy but also has strong adaptability and controllability, and can self-optimize according to different geological conditions, thus providing a more efficient and reliable solution for the pile foundation construction in reclamation areas and other complex strata. Summary of the Invention

[0006] The present invention aims to address the deficiencies in the prior art and provides an automatic speed regulation and grouting adjustment system for the construction of deep mixing piles in reclamation areas, to solve the technical problems that in the construction of reclamation areas, due to the complex and difficult-to-precisely-identify formation changes, traditional methods cannot effectively ensure the mixing sufficiency and grouting quality, thus affecting the overall strength and uniformity of the pile body. To this end, the present invention proposes an intelligent system that can real-time monitor the torque and wear conditions of the drill bit and automatically adjust the construction parameters to cope with the changes in different formations and ensure the stability and consistency of the construction quality.

[0007] The technical solution of the present invention includes an automatic speed regulation and grouting adjustment system for the construction of deep mixing piles in reclamation areas, and the main steps are as follows: S101: Install a multi-modal sensing system for real-time monitoring of key parameters during the construction process; S102: A data acquisition and fusion module time-tags the key parameters through a high-precision synchronization module and down-samples the high-frequency data among them for fusing the key parameters monitored by multiple sensors; S103: Establish a formation response model, predict the formation density through the Extended Kalman Filter (EKF) and Model Predictive Control (MPC) algorithms, set constraint conditions, and optimize the construction parameters to ensure that the soil density reaches the expected target; The objective function:

[0008] Wherein, is the deviation of the density, is the prediction step, is the density predicted at time is the predicted density, is the desired formation density; The constraint conditions include setting a hard limit on the mixing speed and a threshold value of the grouting pressure ; S104: Based on the feedback closed-loop regulation HFB system, the mixing speed and grouting volume are real-time adjusted through a fuzzy PID controller to ensure the construction quality; S105: A construction data storage and self-learning optimization module optimizes the control strategy through a deep reinforcement learning algorithm and uses a time-series database for data management and storage.

[0009] In step S101, the specific operations are as follows: S11: According to the key factors in the construction of deep mixing piles, select a torque sensor, an energy monitoring module, a grouting pressure sensor, and a formation permeability probe, wherein: The torque sensor selects a high-precision dynamic torque sensor for detecting the rotational resistance of the mixing pile; The energy monitoring module integrates a current transformer and a voltage sensor to calculate the power of the mixing motor in real time; The grouting pressure sensor uses a corrosion-resistant piezoresistive sensor to monitor the pressure change during grouting; The formation permeability probe installs a micro void water pressure gauge and indirectly evaluates the formation permeability coefficient through the static cone penetration test principle to evaluate the grouting effect.

[0010] S12: The torque sensor is installed at the output end of the mixing drill pipe head. A set of torque sensors is arranged every 2 meters along the axial direction of the drill pipe to form a distributed monitoring network. The energy monitoring module is installed at the power input section of the electric control system. The grouting pressure sensor is installed on the outlet pipeline of the grouting pump. The formation permeability probe is embedded in the mixing blade in a spiral array and synchronously collects formation data as the drill pipe rotates.

[0011] S13: Set threshold alarms. When the torque exceeds 80% of the set value, a warning is triggered. When the fluctuation range of the grouting pressure > ±15%, the construction is suspended.

[0012] In step S102, the specific operations are as follows: S21: Deploy a high-precision GPS synchronization module (PPS accuracy ±10ns), add a unified time tag to all sensor data, and downsample the high-frequency data to align with the low-frequency data at a common sampling rate of 10Hz.

[0013] S22: Use wavelet threshold denoising for the torque signal, perform real-time moving average filtering on the grouting pressure data, identify outliers based on the isolation forest algorithm, and fill in the missing data using linear interpolation.

[0014] S23: Extract time-domain features (mean, variance) and frequency-domain features (energy in the 5 - 20Hz frequency band) from the torque data, and calculate the dynamic pressure gradient based on the grouting pressure data. Its equation is:

[0015] where, is the pressure at time , is the spatial position at time , is the spatial position at time , is the time step.

[0016] Use the extended Kalman filter (EKF) to fuse the formation permeability, torque, and grouting pressure to generate a 6-dimensional state vector: [formation permeability coefficient, torque mean, pressure gradient, torque variance, frequency band energy, formation density].

[0017] In step S103, the specific operations are as follows: S31: By defining key state variables, establish a model that can predict the formation density First, define the state vector:

[0018] where is the formation permeability coefficient, is the average torque, is the pressure gradient, is the torque variance, is the frequency band energy, is the density.

[0019] Then the observation equation is:

[0020] This function reflects the influence of parameters such as formation permeability coefficient, average torque, pressure gradient, torque variance, and frequency band energy on the formation density.

[0021] S32: Extended Kalman Filter (EKF) is used for state estimation of nonlinear systems to obtain more accurate formation state information. Through iterative processing in the prediction stage and the update stage, EKF can correct the predicted state variables according to sensor data and process noise, providing real-time formation state estimation. This method is particularly suitable for dealing with systems with nonlinear relationships and optimizes the accuracy of the estimation process by setting an appropriate noise covariance matrix.

[0022] S33: With the help of the Model Predictive Control (MPC) algorithm, the system adjusts control parameters such as stirring speed and grouting volume through rolling horizon optimization to minimize the deviation of formation density. MPC sets the prediction horizon (i.e., performs optimization prediction in the future time steps) and the control horizon (i.e., makes a control adjustment every time steps), combines the objective function and constraint conditions, and optimizes parameter adjustment in real time, thus ensuring the stability and efficiency of the construction process. As the control period progresses, MPC continuously re-optimizes the control strategy according to new data to ensure that the soil density reaches the expected target.

[0023] Among them, the objective function is as follows:

[0024] is the deviation of density, is the predicted density at time , is the desired formation density.

[0025] The constraints are as follows: Set a hard limit on the stirring speed and the threshold value of the grouting pressure .

[0026] S34: Online parameter identification is implemented through the recursive least squares (RLS) method, which can update the model coefficients in real time to ensure that the model has strong adaptability to the changing construction environment. The coefficient update is performed every 5 seconds to gradually improve the prediction accuracy of the model. After a certain number of construction piles are completed, offline training and model version update are triggered to ensure continuous optimization of the system, and the latest model is applied to the subsequent construction process.

[0027] In step S104, the specific operations are as follows: S41: Dynamically adjust the stirring speed through a fuzzy PID controller, and the input of this controller is the density deviation , that is, the difference between the current density and the target density, and the output is the adjustment amount of the stirring speed , and the formula is:

[0028] Among them, is the proportional gain, which determines the adjustment amount proportional to the current deviation; is the integral gain, which reflects the influence of past cumulative errors and helps to eliminate steady-state errors; is the derivative gain, which is used to consider the rate of change of the error and helps to reduce oscillations or overshoots.

[0029] If , increase the stirring speed; if , reduce the stirring speed.

[0030] S42: Use the dynamic threshold algorithm to limit the grouting pressure to avoid damage to the equipment caused by overpressure and ensure the construction quality.

[0031] Define the safe range of the grouting pressure , that is, the upper and lower threshold values of the grouting pressure.

[0032] Calculate the deviation according to the real-time pressure data , through the dynamic threshold algorithm, when the grouting pressure exceeds the set dynamic threshold , the control system adjusts the flow rate of the grouting pump through the PID control algorithm to reduce the grouting volume, thereby reducing the pressure, and adjusts the rotation speed or power of the servo motor to slow down the grouting speed, thereby reducing the system pressure.

[0033] When the grouting pressure is lower than the minimum threshold , the system increases the grouting flow rate to raise the pressure.

[0034] According to the construction progress and specific conditions, the dynamic threshold algorithm continuously adjusts the threshold. For example, at different stages of construction, as the grouting volume increases or the pressure changes, the dynamic threshold will change accordingly. This helps to more flexibly respond to pressure fluctuations and prevent the equipment from suffering excessive pressure.

[0035] In addition, a hard limit for the stirring speed is set to prevent equipment damage, as well as an emergency grouting pressure cut-off threshold , once the pressure exceeds the limit, the system automatically cuts off the grouting to avoid irreversible damage to the system caused by excessive pressure and ensure the safety of equipment and personnel during the construction process. S43: Through the real-time feedback control system, based on the data collected by the sensors, the system continuously adjusts the stirring speed, grouting volume and pressure to ensure that the construction process is continuously optimized and maintains the optimal working state. This closed-loop control system ensures construction accuracy and efficiency and adapts to changes under different formation conditions. In step S105, the specific operations are as follows: S51: In data management and storage, the time-series database InfluxDB is used to store all the structured data collected by the sensors, ensuring that the data can be queried and processed according to the timestamp. The sampling interval is set to 1 second to ensure high-precision data recording and real-time requirements. At the same time, the video stream at the construction site is stored using HDFS distributed storage to ensure efficient and reliable storage and management of a large amount of video data, providing a solid data foundation for subsequent analysis and optimization.

[0036] In the DDPG algorithm of reinforcement learning training, through the Actor-Critic structure, it can optimize the system decision-making in a continuous control environment and help automatically adjust key operations such as the stirring speed and grouting volume. The reward function guides the learning through the balance of density and energy consumption to ensure that while the target density meets the requirements, the energy consumption is kept within the lowest range. The form of the reward function is:

[0037] where is the current density, is the target density, is the maximum energy consumption, is the current energy consumption, and are the weight coefficients used to balance the optimization between density and energy consumption.

[0038] Through system training, the model is continuously optimized, and the generated control strategy can cope with the changes in different construction environments, improving the system adaptability. After each training, the strategy is optimized and updated to achieve more precise and efficient construction operations, thereby continuously improving the efficiency and quality during the construction process.

[0039] S53: In the implementation and verification phase, a closed-loop test will be carried out in typical reclamation strata to verify the actual effect of the system. Description of the Drawings

[0040] The drawings are only for illustrative purposes and should not be construed as a limitation to the present solution; for better illustration of the present solution, some components in the drawings are omitted, enlarged or reduced, which do not represent the dimensions of the actual product; for those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0041] Figure 1 is a flow chart of an automatic speed regulation and grouting adjustment system for deep mixing pile construction in a reclamation area of the present invention; Figure 2 is a sectional view of the drill pipe structure and sensor deployment; Figure 3 is a schematic diagram of the structure of the mixing bit; Figure 4 is a schematic diagram of the formation response model; Figure 5 is a schematic diagram of the system operation interface.

[0042] The reference numerals in the specification include: tower 001, power head 002, mixing drill pipe 003, torque sensor 004, mixing bit 005, base 006, energy monitoring module 007, electric control system 008, grouting pipe 009, high-pressure mud pump 010, grouting pressure sensor 011, mixing blade 012, mixing member 013, formation permeability probe 014. Detailed Embodiments

[0043] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the 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.

[0044] Embodiment: Refer to Figures 1 to 5 Particularly, as Figure 1As shown, an automatic speed regulation and grouting adjustment system for deep mixing pile construction in reclamation areas provided by the present invention aims to improve construction quality and efficiency by dynamically adjusting construction parameters in real time. It adopts a "energy regulation - formation response" bivariate control method and combines a phased construction regulation strategy to ensure the accuracy and adaptability of the construction process. The implementation steps are as follows: Step S101: The sensor module includes a torque sensor, a wear detection device, a pressure sensor, a flow sensor, and a formation permeability probe. Each sensor collects the mixing speed, grouting pressure, grouting flow rate, and formation density in real time and transmits the data to the data acquisition module through a combination of wired and wireless networks.

[0045] The data acquisition and fusion module in step S102 includes a data collector, a signal amplifier, a data converter, and a data fusion algorithm. The raw data collected by the sensors is enhanced by the signal amplifier and converted into a standard signal format suitable for transmission and processing by the data converter. Subsequently, the data fusion algorithm integrates and calibrates the multi-source data and transmits the processed data to the central control system through a data bus for subsequent analysis and decision-making.

[0046] Step S103: The system constructs a formation response model using the Extended Kalman Filter (EKF) and Model Predictive Control (MPC) algorithms. By analyzing the formation and grouting data collected by the sensors, the system establishes a relationship model between the formation input and the formation response. This model evaluates the formation density and grouting quality in real time, intelligently analyzes the formation changes during the construction process, and provides a basis for construction adjustment, thereby optimizing the construction effect.

[0047] Step S104 includes a feedback closed-loop control system that performs dynamic control using the aforementioned formation response model, real-time data, and intelligent algorithms. The fuzzy PID controller adjusts the mixing speed according to the density deviation and adjusts the control signal of the grouting pump according to the grouting volume deviation to ensure accurate and uniform grouting. The dynamic threshold algorithm is used to limit the grouting pressure to avoid damage to the equipment caused by overpressure. The grouting flow rate is adjusted according to the real-time pressure data to keep the grouting pressure within a safe range. Through this feedback mechanism, the system can adaptively adjust the construction parameters to ensure precise control and dynamic optimization of the construction process.

[0048] Step S105: The time series database InfluxDB is used to store all the structured data collected by the sensors to ensure high-precision data recording and real-time requirements. At the same time, the HDFS distributed storage is used to manage a large amount of video data. The DDPG algorithm is used in the reinforcement learning training to optimize key operations such as mixing speed and grouting volume to ensure the accuracy and efficiency of the construction process.

[0049] Through the collaborative work of a multi-modal sensing system, a data acquisition and fusion module, a formation response model, a feedback closed-loop control system, and a construction data storage and self-learning optimization module, the present invention breaks through the limitations of traditional single-parameter optimization methods. This system can adaptively adjust construction parameters in real time, achieve dual-variable control of energy-formation and dynamic optimization throughout the process, and significantly improve the safety, uniformity, and construction efficiency of deep mixing pile construction in reclamation areas.

[0050] In particular, Figure 2 shows the overall scheme of the drill pipe structure and sensor deployment and its working process. The core system includes sensor configuration, data acquisition, data processing and intelligent algorithm judgment, automatic adjustment, and feedback mechanism. In particular, it includes step S101, where sensors are arranged during the drilling operation, including a torque sensor 004, a formation permeability probe 014, a grouting pressure sensor 011, and an energy monitoring module 007, which collect the torque, formation permeability, and grouting pressure of the mixing drill pipe 003 in real time and transmit them to the data acquisition module through a combination of wired and wireless networks.

[0051] The torque sensor 004 is installed at the output end of the mixing drill pipe 003. Among them, a set of torque sensors 004 is arranged every 2 m along the axial direction of the drill pipe to form a distributed monitoring network. The energy monitoring module 007 is installed at the power input section of the electric control system 008, and the grouting pressure sensor 011 is installed at the outlet pipeline of the grouting pipe 009 of the high-pressure mud pump 010. The formation permeability probe 014 is embedded in the mixing blade 012 in a spiral array and collects formation data synchronously with the rotation of the mixing drill pipe 003.

[0052] As Figure 3 shown, it shows the structural schematic diagram of the mixing bit 005. The mixing bit mainly includes: Mixing drill pipe 003: Connects the power head 002 and the mixing bit 005, and transmits the rotational power of the power head 002 to the mixing bit 005; Mixing blade 012: Used to mix soil, cement slurry, or other materials to make them fully mixed; Formation permeability probe 014: Used to detect the permeability of the formation and help determine grouting parameters.

[0053] The formation permeability probe 014 is marked with a green triangle on the structural schematic diagram of the mixing bit 005. The blue dotted line represents the movement trajectory of the formation permeability probe 014 during rotation or mixing in the construction process. The probe moves with the rotation of the mixing bit 005, so as to detect the formation permeability at different positions and provide more comprehensive formation permeability data.

[0054] In particular, attached Figure 4It shows a schematic diagram of the formation response model. The core system includes data preprocessing, intelligent control algorithms, execution layer regulation, and feedback mechanisms. In particular, the data acquisition system including step S102 consists of a data collector, a signal amplifier, and a data converter, which collects the raw data sent by the sensors and converts it into a signal format suitable for transmission and processing. In particular, it includes step S103. The data in the data acquisition module is docked with the central control system through a data bus. The data processing module in the central control system performs preprocessing tasks such as cleaning, denoising, and isolation forest outlier detection on the received raw data to ensure the accuracy and reliability of the data. The data processed by EKF filtering is sent to the intelligent algorithm analysis module for formation density assessment, grouting quality analysis, construction status judgment, etc.

[0055] In particular, it includes step S104. The intelligent control system uses a PID control strategy to adjust the grouting flow rate and the rotation speed of the servo motor. Among them, the proportional (P) control adjusts the grouting pressure in real time, the integral (I) control eliminates the cumulative error, and the derivative (D) control predicts the change trend to prevent overshoot. The intelligent algorithm adjusts the control parameters according to the real-time pressure feedback to maintain a stable grouting pressure, and combines with the MPC (model predictive control) optimization strategy to predict the system response in a short time, dynamically adjust the construction parameters, and improve the control accuracy. The hard limit protection mechanism is used to prevent the system from operating beyond the safe range. The maximum rotation speed of the mixing shaft and the upper limit of the grouting pressure are set as forced constraint conditions. When the system detects that the construction parameters are close to the safety threshold, the intelligent algorithm will adjust the parameters in advance. If it exceeds the safe range, it will immediately trigger an emergency stop. The emergency cut-off mechanism is responsible for protecting the construction safety in extreme cases. When the grouting pressure exceeds the maximum grouting pressure or the mixing speed exceeds the maximum speed, the system immediately executes the emergency stop process, cuts off the operation of the grouting pump, and sends a high-priority alarm message to the operator to ensure the safety of the construction site.

[0056] In particular, it includes step 105. The system adopts a dynamic feedback mechanism to record the adjusted construction parameters and optimization results in the database for further use in construction quality assessment and system optimization. The historical data will be used to improve the dynamic threshold calculation model and provide optimization suggestions for subsequent construction, forming a closed-loop control system to achieve the intelligence and adaptive optimization of the construction process.

[0057] Such as Figure 4As shown in the figure, key parameters during the construction process are monitored in real time in the environment through the sensor module and transmitted to the data acquisition module. The key parameters include torque, formation permeability, grouting pressure, etc. These key parameters are input into the data preprocessing module. After preprocessing operations such as cleaning, denoising, and isolation forest outlier detection on the received raw data, the data processed by EKF filtering is sent to the MPC rolling optimization algorithm and PID control algorithm modules for formation density evaluation, grouting quality analysis, construction status judgment, etc., to generate an optimal control strategy and generate a control signal based on the system error. Then, the PID controller regulation decision module determines whether there are abnormalities or potential risks in the system based on the state prediction result and the preset threshold. If there are abnormalities, specific abnormal situations are output to the staff through the human-machine interaction system. The staff sends manual instructions to the adjustment output module, and the adjustment output module sends instructions to the central control system to dynamically adjust the output parameters of the system. After receiving the instructions, the central control system sends instructions to the execution template, and the execution template performs specific operation tasks according to the sent instructions to achieve the actual control function of the system.

[0058] In particular, Figure 5 The main functions and user interaction part of the central control system operation interface are shown, including the content of step S105 and step S106. At the top of the interface is the navigation bar, spanning the entire screen, including main function options, help, user login, and notification center, facilitating quick access to different function modules. The main function options include: Real-time monitoring is used to obtain real-time construction status, construction parameters, and construction status, etc.; Historical data is used to store various historical data of the construction, enabling the system to establish a formation response model and optimize the control strategy through the deep reinforcement learning algorithm for self-learning optimization; System settings allow the staff to make adjustments to the system display interface, etc., to better conform to the usage habits of the staff; Report generation can automatically generate a warning report based on the results of anomaly detection and risk assessment. The report content includes a detailed description of the abnormal situation, the evaluated risk level and its impact range, recommended handling measures for the abnormal situation, such as adjusting construction parameters, increasing monitoring frequency, etc., as well as graphical risk assessment results and the change trend of key parameters during the construction process to help construction personnel and decision-makers quickly understand.

[0059] On the left is the real-time monitoring panel, occupying the left one-third of the screen. The real-time monitoring panel includes: Construction status, used to display real-time construction parameters, including mixing pile number, current depth, mixing speed, grouting pressure, formation permeability coefficient, torque, formation density; A real-time chart for graphically presenting the risk assessment results and the changing trends of key parameters during the construction process; The alarm indicator lights include abnormal, suspected abnormal, and normal indicator lights, through which the staff can quickly confirm the construction status.

[0060] On the right is the construction control panel, which occupies two-thirds of the right side of the screen. The construction control panel includes: a manual parameter adjustment module, through which parameters can be adjusted by manually pulling the parameter bar left or right; It also includes operation control buttons on the left and mode switching buttons on the right. The operation control buttons are divided into start, pause, and stop, and the mode switching buttons are divided into manual and automatic. The staff can select the current system working status by pressing the buttons, which is simple and easy to understand; The construction control panel also includes a real-time data input box, through which the staff can manually input accurate construction parameter values to adjust the construction status.

[0061] At the bottom of the interface is the system status panel, which spans the entire screen and displays system health status indicators, device status monitoring, and the system diary window. Through the top navigation bar, users can enter the historical data and report panel, as well as the help and support panel, which are usually presented in the form of pop-up windows or new pages.

Claims

1. An automatic speed regulation and grouting regulation system for deep mixing pile construction in reclamation areas, characterized in that: The following steps are involved: S101: Install a multimodal sensing system to monitor key parameters during construction in real time; S102: a data acquisition and fusion module, which time-tags the key parameters through a high-precision synchronization module and downsamples the high-frequency data therein to fuse the key parameters monitored by multiple sensors; S103: Establish a formation response model, predict the formation density through the extended Kalman filter EKF and model predictive control MPC algorithm, set constraints and optimize construction parameters to ensure that the soil density reaches the expected target; The objective function: in, is the density deviation, is the prediction step length, For the moment The predicted density, is the desired formation density; The constraints include setting a hard limit on the stirring speed and the threshold value of grouting pressure ; S104: Based on the feedback closed-loop control of the HFB system, the stirring speed and grouting volume are adjusted in real time through the fuzzy PID controller to ensure the construction quality; S105: Construction data storage and self-learning optimization module, which optimizes the control strategy through deep reinforcement learning algorithm and uses time series database for data management and storage.

2. The automatic speed regulation and grouting regulation system for deep mixing pile construction in reclamation areas according to claim 1 is characterized in that: The multimodal sensing system in step S101 includes a torque sensor, an energy monitoring module, a grouting pressure sensor and a formation permeability probe; The torque sensor is used to monitor the rotational resistance of the mixing pile, the energy monitoring module is used to calculate the power of the mixing motor in real time, the grouting pressure sensor is used to monitor the change of grouting pressure, and the formation permeability probe indirectly evaluates the formation permeability coefficient through the static penetration principle to evaluate the grouting effect.

3. The automatic speed regulation and grouting regulation system for deep mixing pile construction in reclamation areas according to claim 2 is characterized in that: The torque sensor is installed at the output end of the stirring drill rod head, and a group of sensors is arranged every 2 meters; The grouting pressure sensor is installed on the outlet pipeline of the grouting pump; The formation permeability probe is embedded in the stirring blade and collects data synchronously with the rotation of the drill pipe.

4. The automatic speed regulation and grouting regulation system for deep mixing pile construction in reclamation areas according to claim 1 is characterized in that: The data acquisition and fusion module in step S102 also includes a high-precision GPS synchronization module for time synchronization, and uses an extended Kalman filter (EKF) algorithm to fuse the formation permeability, torque and grouting pressure data to generate a 6-dimensional state vector: [formation permeability, torque mean, pressure gradient, torque variance, frequency band energy, formation density].

5. The automatic speed regulation and grouting regulation system for deep mixing pile construction in reclamation areas according to claim 1 is characterized in that: The deep reinforcement learning optimization algorithm described in step S105 continuously optimizes the control strategy according to historical data during the construction process to improve construction accuracy.

6. The automatic speed regulation and grouting regulation system for deep mixing pile construction in reclamation areas according to claim 1 is characterized in that: In step S103, the formation response model optimizes control parameters according to real-time formation status and construction data through the model predictive control MPC algorithm to minimize the deviation of formation density, and the control parameters include stirring speed and grouting volume.

7. The automatic speed regulation and grouting regulation system for deep mixing pile construction in reclamation areas according to claim 1 is characterized in that: The feedback closed-loop control system in step S104 adjusts the stirring speed and grouting volume through a fuzzy PID controller, specifically adjusting the stirring speed and the grouting pump flow rate through real-time feedback to ensure accuracy and uniformity during the construction process.

8. The automatic speed regulation and grouting regulation system for deep mixing pile construction in reclamation areas according to claim 7 is characterized in that: The fuzzy PID controller adjusts the stirring speed and the grouting amount according to the density deviation, and the grouting pump flow control ensures the grouting accuracy and uniformity by adjusting the servo motor speed or power in real time.

9. The automatic speed regulation and grouting regulation system for deep mixing pile construction in reclamation areas according to claim 8, characterized in that: Step S104 specifically includes: S41: Dynamically adjust the stirring speed through the fuzzy PID controller, the input of which is the density deviation , that is, the difference between the current density and the target density, and the output is the adjustment amount of the mixing speed : in, is the proportional gain, which determines the adjustment amount proportional to the current deviation; is the integral gain, which reflects the influence of past accumulated errors and helps to eliminate steady-state errors; is the differential gain, which is used to take into account the rate of error change and help reduce oscillation or overshoot; if , then increase the stirring speed; if , then reduce the stirring speed; S42: Use dynamic threshold algorithm to limit grouting pressure to avoid damage to equipment caused by overpressure and ensure construction quality; Defining the safe range of grouting pressure , i.e., the upper and lower thresholds of grouting pressure; Calculate deviation based on real-time pressure data , through the dynamic threshold algorithm, when the grouting pressure Exceeds the set dynamic threshold ,The control system adjusts the flow rate of the grouting pump through the PID control algorithm, reduces the grouting volume, thereby reducing the pressure, and slows down the grouting speed by adjusting the speed or power of the servo motor, thereby reducing the system pressure; When the grouting pressure Below the minimum threshold , the system increases the pressure by increasing the grouting flow; A hard limit is set for the stirring speed To prevent equipment damage and emergency grouting pressure cut-off threshold , when the emergency grouting pressure cut-off threshold is exceeded When the pressure is too high, the system automatically cuts off the grouting to avoid irreversible damage to the system caused by excessive pressure; S43: Through the real-time feedback control system, the system continuously adjusts the mixing speed, grouting volume and pressure according to the data collected by the sensors to ensure continuous optimization of the construction process and maintain the optimal working state.

10. The automatic speed regulation and grouting regulation system for deep mixing pile construction in reclamation areas according to claim 1, characterized in that: The construction data storage and self-learning optimization module in step S105 uses a time series database to store sensor data, and optimizes the control strategy through a reinforcement learning algorithm to generate control strategies for different construction environments to improve construction efficiency and quality.

Images