Intelligent construction control method and system for rotary jetting pile based on stratum information inversion

Abstract

This invention belongs to the field of pile foundation technology and provides an intelligent construction control method and system for jet grouting piles based on stratum information inversion. It integrates multiple sensing components and transmits data locally to a data integration terminal in real time, sensing borehole information. Using engineering soil layer data as training samples, it establishes a correspondence between sensed information and geological conditions based on machine learning algorithms, judging and outputting stratum conditions in real time. Through the XGBoost machine learning model learning from the samples, it achieves rapid and accurate identification of soil layers at the work site. Based on cloud platform big data matching, it establishes an optimal construction parameter database, obtaining the optimal combination of construction parameters through algorithm matching. Variable frequency speed and pressure regulation equipment enables the intelligent control system of the pile driver to link with other subsystems, achieving intelligent control of the construction process. This invention effectively reduces material consumption in jet grouting pile construction and improves pile quality and efficiency.

Description

Technical Field

[0001] This invention belongs to the field of pile foundation technology, and in particular relates to an intelligent construction control method and system for jet grouting piles based on stratum information inversion. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Jet grouting piles are widely used in foundation reinforcement and waterproofing curtains. They involve drilling a grouting pipe with a nozzle to a predetermined location in the soil layer using a drilling rig, or drilling a hole first and then placing the grouting pipe in the predetermined location. High pressure forces grout or water out of the nozzle, and the grout is injected while the rig rotates, mixing with the soil to form a cement-soil pile. The diameter and quality of jet grouting piles are closely related to soil conditions and construction conditions, including borehole diameter, injection method, nozzle diameter, injection pressure, grout mix ratio, and grouting pipe lifting speed. Mismatches between construction conditions and soil conditions (such as improper matching of injection pressure, pipe pulling speed, rotation speed, and grout volume) can easily lead to serious problems such as uneven strength of the consolidated body, necking, material waste, and low construction efficiency. Therefore, to comprehensively ensure pile quality and construction efficiency, dynamic control based on soil conditions is necessary. In engineering projects, a site with similar conditions is usually selected within the construction site for on-site testing to determine the construction process parameters. However, the geological conditions in the project are complex, and the actual geological distribution is not consistent with the geological distribution of the test site. Therefore, the construction process parameters are often not suitable for the actual soil layer of the project, resulting in low construction efficiency and poor quality of some jet grouting piles, and even pile breakage.

[0004] Currently, commonly used jet grouting equipment includes a high-pressure pump, a grout mixer, a drilling rig with drill rods, and a power head device that drives the drill rods to rotate. Existing technology determines soil layer distribution based on the real-time monitoring of the current value of the drilling rig's power head during construction. However, the current value is not only related to the soil layer type but is also affected by factors such as penetration pressure, velocity, and depth. Therefore, directly determining soil layer distribution and controlling construction process parameters based on the current value is inaccurate. Summary of the Invention

[0005] To address at least one of the technical problems existing in the background art, the first aspect of the present invention provides an intelligent construction control method and system for jet grouting piles based on stratum information inversion. It uses drilling depth, drilling rig output power, drill rod axial force, drill bit torque, and pore water pressure as initial data to invert stratum information in real time, match optimal construction parameters, and intelligently control the construction process to reduce material consumption costs and improve pile quality and efficiency.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] The first aspect of the present invention provides an intelligent construction control method for jet grouting piles based on geological information inversion, comprising the following steps:

[0008] Obtain construction data during the drilling process;

[0009] By combining drilling process data with XGBoost machine learning model, formation inversion data is obtained.

[0010] Based on stratigraphic inversion data and a self-learning parameter matching model, the optimal combination of construction parameters is obtained by matching the optimal construction parameter database.

[0011] The intelligent adjustment module for construction parameters and the self-learning parameter matching model are linked. When the inversion data of the stratum changes, the self-learning parameter matching model is updated in real time to obtain the updated optimal combination of construction parameters. The intelligent adjustment module for construction parameters automatically adjusts the construction parameters by controlling the variable frequency speed and pressure regulating equipment according to the updated optimal combination of construction parameters, so that the entire construction process of the jet grouting pile is carried out with the optimal construction parameters.

[0012] A second aspect of the present invention provides an intelligent construction control system for jet grouting piles based on geological information inversion, comprising:

[0013] The construction process self-sensing module is used to acquire construction data during the drilling process;

[0014] The real-time formation information inversion module is used to combine drilling process data and XGBoost machine learning model to perform inversion and obtain formation inversion data.

[0015] The construction parameter self-matching module is used to obtain the optimal combination of construction parameters based on the formation inversion data and the self-learning parameter matching model, and based on the optimal construction parameter database.

[0016] The intelligent control module for pile foundations is used to link the intelligent adjustment module for construction parameters and the self-learning parameter matching model. When the inversion data of the stratum changes, the self-learning parameter matching model is updated in real time to obtain the updated optimal combination of construction parameters. The intelligent adjustment module for construction parameters automatically adjusts the construction parameters by controlling the variable frequency speed and pressure regulating equipment according to the updated optimal combination of construction parameters, so that the entire construction process of jet grouting piles is carried out with optimal construction parameters.

[0017] A third aspect of the present invention provides a computer-readable storage medium.

[0018] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the intelligent construction control method for jet grouting piles based on stratum information inversion as described in the first aspect.

[0019] A fourth aspect of the present invention provides a computer device.

[0020] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the intelligent construction control method for jet grouting piles based on geological information inversion as described in the first aspect.

[0021] Compared with the prior art, the beneficial effects of the present invention are:

[0022] 1. This invention achieves intelligent control of the construction process by linking a variable frequency speed regulation device with a construction parameter self-matching system, so that the entire process of jet grouting pile construction can be carried out according to the optimal construction parameters.

[0023] 2. This invention integrates multi-source sensing components and transmits data locally to monitor drilling depth and drilling machine output power in real time, and senses torque, axial force and pore water pressure during the drilling process, thereby achieving accurate monitoring of key parameters in the drilling process.

[0024] 3. The present invention establishes a correspondence between perceived information and geological conditions based on machine learning algorithms, and judges and outputs the stratum conditions in real time, thereby improving the accuracy of stratum distribution inversion during jet grouting pile construction.

[0025] 4. This invention establishes an optimal construction parameter database that can be continuously updated and expanded based on cloud platform big data matching. The optimal combination of construction parameters is obtained through algorithm matching, which effectively reduces material consumption and improves pile quality and pile efficiency.

[0026] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0027] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0028] Figure 1 A flowchart illustrating the steps of an intelligent construction method for jet grouting piles based on real-time inversion of geological information, as provided in an embodiment of the present invention.

[0029] Figure 2 A schematic diagram of the intelligent construction control system for jet grouting piles based on real-time inversion of geological information provided in an embodiment of the present invention;

[0030] Figure 3 This is a sensor layout diagram provided in an embodiment of the present invention;

[0031] Figure 4 The algorithm flowchart of the XGBoost model provided in the embodiments of the present invention;

[0032] Figure 5 A model diagram of a single neuron structure provided in an embodiment of the present invention.

[0033] In the diagram: 1. Tripod, 2. Winch, 3. Grouting pipe, 4. Mixer, 5. Jet jet pipe, 6. Rotary flow meter, 7. Grout storage tank, 8. Grout storage pool, 9. Screen, 10. High-pressure jet jet drilling rig, 11. Drill rod, 12. Orifice device, 13. Air compressor, 14. High-pressure variable frequency pump, 15. Drill bit, 16. Grouting layer, 17. Wireless signal, 18. Hub, 19. Microcontroller, 20. Data integration terminal, 21. Torque sensor, 22. Pore water pressure sensor, 23. Axial force sensor. Detailed Implementation

[0034] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0035] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0036] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0037] Example 1

[0038] This embodiment provides an intelligent construction control method for jet grouting piles based on geological information inversion, including the following steps:

[0039] S1, Install torque sensor 21 and pore water pressure sensor 22 on drill bit 15, install axial force sensor 23 on the lower part of drill rod 11, and complete the calibration of the sensors;

[0040] S2, move the high-pressure jet grouting drill 10 to the designated position, align the drill bit 15 with the center of the hole, and at the same time level the high-pressure jet grouting drill 10, placing it stably and horizontally;

[0041] S3, Drill a hole at a designated location, use a high-pressure jet grouting drill 10 to monitor the drilling depth and the output power of the drill in real time, and use a torque sensor 21, a pore water pressure sensor 22, and an axial force sensor 23 to sense the torque, pore water pressure, and axial force during the drilling process in real time.

[0042] S4, the wireless sensor network system receives the sensor wireless signal 17 and uploads the data to the data integration terminal 20;

[0043] S5 takes the received data as the input layer of the XGBoost machine learning model, and the output layer is the soil type, strength, water content and permeability coefficient.

[0044] S6 inputs the output soil layer type, strength, moisture content and permeability coefficient into the self-learning parameter matching module in the data integration terminal 20, and matches the best combination of construction parameters based on the optimal construction parameter database;

[0045] S7 inputs the optimal combination of construction parameters into the intelligent adjustment module of construction parameters in the data integration terminal 20, and automatically adjusts the construction parameters through the variable frequency speed and pressure regulating equipment (drilling drive motor and high-pressure variable frequency pump) to realize intelligent control of the construction process;

[0046] S8. Prepare cement slurry according to the optimal mud ratio output. First, add water to mixer 4, then pour in cement and admixtures, start the mixer and mix. After mixing, unscrew the valve on the right side of the mixer, pour into the screen 9 for filtration and flow into the slurry storage tank 8, and then pump it into the slurry storage tank 7 for later use through the mud pump.

[0047] S9. After drilling to the design depth, install the jet grouting pipe 5. After the jet grouting pipe 5 is inserted to the predetermined depth, the spraying operation is carried out from bottom to top. The construction is carried out according to the matching spraying pressure, lifting speed and rotation speed. The jet grouting pipe is lifted and rotated at the same time until the design length is reached and then the spraying is stopped.

[0048] S10. After the jet grouting operation is completed, due to the water separation effect of the grout, the solidified body generally shrinks to varying degrees, causing a depression at the top. It is necessary to replenish the grout in time. Open the valve on the left side of the grout storage tank 7 and spray static pressure grout into the hole through the grouting pipe 3 until the solidified body in the hole no longer sinks.

[0049] S11. Inject an appropriate amount of clean water into the slurry storage tank 7, turn on the high-pressure variable frequency pump 14, clean the residual cement slurry in all pipelines until it is basically clean, and clean the soil adhering to the rotary jet nozzle head.

[0050] S12, move the high-pressure jet grouting drilling rig 10 to the next construction position, and repeat the above steps to complete the construction of the jet grouting pile.

[0051] In S3 above, when the drill bit drills in different depths and different types of soil layers, the torque at the drill bit, the pore water pressure, the axial force of the drill rod, and the output power of the drilling machine are all different. Multi-source sensing devices are used to sense the above parameters in real time as a basis for judging the soil layer type.

[0052] In step S4 above, the sensor wireless signal is emitted from below the ground and is affected by the real-time drilling of the drill bit. To ensure the stability and accuracy of signal transmission, a hub is set up between the wireless signal and the receiving terminal to regenerate, shape and amplify the received signal, thereby expanding the signal transmission distance and maintaining signal stability.

[0053] In step S5 above, the XGBoost model balances speed and efficiency, enhancing gradient boosting performance. Employing a parallel tree boosting method accelerates model learning, allows it to run on different platforms and in various languages, and strengthens its non-linear learning capabilities and scalability, thus offering significant advantages in terms of efficiency and portability for prediction problems and practical applications. The XGBoost model algorithm flowchart is shown below. Figure 4 As shown, the specific construction process is as follows:

[0054] This invention uses a large database of engineering soil properties as training samples, and uses borehole depth, torque, axial force, pore water pressure and output power as the input layer of the model to establish the correspondence between the perceived information and the geological conditions. It uses soil type, strength, water content and permeability coefficient as the output layer to predict the geological conditions and retrieve the geological information in real time.

[0055] The XGBoost machine learning model continuously optimizes its parameters by learning from training samples, improving the efficiency and accuracy of identifying soil types at different depths. The identified soil types are basic soil types, such as sand, silt, and clay.

[0056] In step S6 above, the self-learning parameter matching system uses an artificial neural network to represent the construction parameter matching model as a mapping relationship with multiple inputs and multiple outputs:

[0057] f:Y=f(x)

[0058] In the formula, x is the input vector, x = (α1, α2, α3, ... α n ),α1-α n Representing the construction parameter components, Y is the output vector, Y = (β1, β2, β3, ..., β2). n ),β1-β n This represents the output performance component.

[0059] The construction parameter matching model is constructed by interconnecting a large number of processing units in some way; its basic unit is called a neuron. In a neural network, each neuron receives input signals from other neurons connected to it. Each input signal corresponds to a weight, and the weighted sum of all received signals determines the neuron's activation state. These neurons have local memory and can perform local operations. Each neuron has a single output connection, which can branch into several parallel connections as needed, outputting the same signal regardless of the number of parallel connections.

[0060] like Figure 5 As shown, the structure of a single neuron can be divided into input signal, input signal weights, external input signal, activation function, and output signal. Where x... l ,x2…x j …x n Indicates the input signal, w ij The weights of the input signal, s i Let f(·) be the external input signal, and y be the activation function. i This represents the output signal. The above model can be expressed as:

[0061]

[0062] The construction process of the self-learning parameter matching model includes: using an artificial neural network to implicitly express the mapping relationship, taking the data of construction parameters and pile quality as samples, inputting them into the constructed neural network for training, finding the nonlinear mapping relationship between the jet grouting pile construction parameters and the pile quality, storing this nonlinear mapping relationship on the connection weights of the input and output neurons, taking the jet grouting pile construction parameters as input and the pile quality as output, and obtaining the optimal combination of construction parameters through algorithm matching.

[0063] Furthermore, the mechanisms by which various construction parameters affect pile quality are complex and difficult to express with explicit mathematical expressions.

[0064] Therefore, the construction process of the self-learning parameter matching model includes:

[0065] The method uses an artificial neural network model to implicitly express the relationship between construction parameters and pile quality. This involves inputting the data of construction parameters and pile quality into the constructed neural network for training, finding the nonlinear mapping relationship between the jet grouting pile construction parameters and the pile quality, and storing this nonlinear mapping relationship in the connection weights of the input and output neurons. The jet grouting pile construction parameters are used as input quantities, and the pile quality is used as output quantities. The optimal combination of construction parameters is obtained through algorithm matching.

[0066] The optimal construction parameter database consists of jet grouting pile construction parameters under typical geological conditions obtained from a cloud platform, including mud ratio, mud volume, grouting pressure and grouting speed, as well as drilling speed, drill rod lifting speed and jet grouting pipe rotation speed.

[0067] This model features automatic learning, eliminating the need for a pre-established ideal model. It learns from the provided engineering construction data and adaptively establishes the mapping relationship between parameters, overcoming the difficulties of nonlinear mathematical modeling in traditional methods.

[0068] Furthermore, the optimal construction parameter database of the self-learning parameter matching system accumulates data on soil properties, construction parameters, and pile quality from existing jet grouting pile construction. The database supports updates and optimizations, ensuring the timeliness and applicability of the built-in data. Inputting the soil type, strength, moisture content, and permeability coefficient identified in the previous step, the self-learning parameter matching system automatically matches the construction parameters of jet grouting piles in the database, and outputs the optimal construction parameters based on an artificial neural network, with pile quality as the objective.

[0069] In step S7 above, the intelligent adjustment system for construction parameters is linked with the self-learning parameter matching system. When the soil type, strength, moisture content and permeability coefficient change, the self-learning parameter matching system updates the optimal construction parameters in real time. The intelligent adjustment system for construction parameters automatically adjusts the lifting speed and rotation speed and other construction parameters through the variable frequency speed-regulating pressure device according to the updated optimal parameter combination, so that the optimal construction parameters are used throughout the entire construction process of the jet grouting pile, thereby improving the quality and efficiency of pile formation.

[0070] The variable frequency speed and pressure regulating equipment includes a drilling drive motor and a high-pressure variable frequency pump. The drilling drive motor controls the drilling speed, the drilling rod lifting speed, and the rotation speed of the jet grouting pipe, while the high-pressure variable frequency pump controls the grouting pressure and the grouting speed.

[0071] Example 2

[0072] This embodiment provides an intelligent construction control system for jet grouting piles based on stratum information inversion, including: a construction process self-sensing module, a stratum information real-time inversion module, a construction parameter self-matching module, and a pile driver intelligent control module.

[0073] The self-sensing module for the construction process includes a drilling rig, multi-source sensing components, a wireless sensor network system, and a data integration terminal; the real-time inversion system for geological information includes an XGBoost machine learning model and engineering geological data training samples; the self-matching system for construction parameters includes an optimal construction parameter database and a self-learning parameter matching system; and the intelligent control system for pile drivers includes variable frequency speed regulation equipment and an intelligent adjustment system for construction parameters.

[0074] The drilling rig is a high-pressure rotary jet grouting rig, capable of real-time monitoring of drilling depth and rig output power. The multi-source sensing components are vibrating wire sensors, including a torque sensor and a pore water pressure sensor mounted at the drill bit, and an axial force sensor mounted at the bottom of the drill rod. By using the drilling rig and multi-source sensing components to sense drilling depth, torque, axial force, pore water pressure, and rig output power in real time, drilling depth, torque, axial force, pore water pressure, and output power are used as input parameters for formation inversion.

[0075] The wireless sensor network system includes a wireless transceiver chip, a low-power microcontroller 19, a hub 18, and a receiving terminal module, which are used to receive sensor data and transmit it to a data integration terminal 20.

[0076] Preferably, the microcontroller is an embedded ultra-low power microcontroller, which has the advantages of fast operation speed, strong stability and low power consumption.

[0077] Preferably, the hub is a stacked hub, which regenerates and expands the received signal to extend the network transmission interval and quickly transmit port data to the terminal system.

[0078] The data integration terminal is used to receive sensor signals, display sensor data, and input the data into the real-time formation information inversion module.

[0079] The real-time formation information inversion module is used to combine data on borehole depth, output power, torque, axial force, and pore water pressure during the drilling process with the XGBoost machine learning model to invert and obtain formation inversion data.

[0080] The construction parameter self-matching module is used to obtain the optimal combination of construction parameters based on the formation inversion data and the self-learning parameter matching model, and based on the optimal construction parameter database.

[0081] The intelligent adjustment module for construction parameters is connected to the self-matching system for construction parameters. It receives the optimal construction parameters transmitted by the self-matching system and controls the construction parameters in real time through variable frequency speed regulation equipment, thereby realizing intelligent control of the construction process and ensuring that the construction is carried out according to the optimal construction parameters.

[0082] Specifically, this includes linking the intelligent adjustment module for construction parameters with the self-learning parameter matching model. When the inversion data of the stratum changes, the self-learning parameter matching model updates in real time to obtain the updated optimal combination of construction parameters. The intelligent adjustment module for construction parameters automatically adjusts the construction parameters by controlling the variable frequency speed and pressure regulating equipment according to the updated optimal combination of construction parameters, so that the entire construction process of the jet grouting pile is carried out according to the optimal construction parameters.

[0083] Example 3

[0084] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the intelligent construction control method for jet grouting piles based on stratum information inversion as described in Embodiment 1.

[0085] Example 4

[0086] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the intelligent construction control method for jet grouting piles based on stratum information inversion as described in Embodiment 1.

[0087] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0088] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0089] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0090] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0091] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0092] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A jet grouting pile intelligent construction control method based on stratum information inversion, characterized in that, Includes the following steps: Obtain construction data during the drilling process; By combining drilling process data with XGBoost machine learning model, formation inversion data is obtained. Based on stratigraphic inversion data and a self-learning parameter matching model, the optimal combination of construction parameters is obtained by matching the optimal construction parameter database. The construction process of the self-learning parameter matching model includes: using an artificial neural network to implicitly express the mapping relationship, taking construction parameters and pile quality data as samples, inputting them into the constructed neural network for training, finding the nonlinear mapping relationship between jet grouting pile construction parameters and pile quality and efficiency, storing this nonlinear mapping relationship on the connection weights of input and output neurons, taking jet grouting pile construction parameters as input and pile quality as output, and obtaining the optimal combination of construction parameters through algorithm matching; The intelligent adjustment module for construction parameters and the self-learning parameter matching model are linked. When the inversion data of the stratum changes, the self-learning parameter matching model is updated in real time to obtain the updated optimal combination of construction parameters. The intelligent adjustment module for construction parameters automatically adjusts the construction parameters by controlling the variable frequency speed and pressure regulating equipment according to the updated optimal combination of construction parameters, so that the entire construction process of the jet grouting pile is carried out according to the optimal construction parameters.

2. The intelligent construction control method for jet grouting piles based on geological information inversion as described in claim 1, characterized in that, The construction process of the XGBoost machine learning model is as follows: Engineering geological data is used as training samples for training. Drilling depth, torque, axial force, pore water pressure and output power are used as input layers for the model to establish the correspondence between perceived information and geological conditions. Soil type, strength, water content and permeability coefficient are used as output layers for geological prediction and real-time inversion of geological information.

3. The intelligent construction control method for jet grouting piles based on geological information inversion as described in claim 1, characterized in that, In the self-learning parameter matching model, each neuron in the neural network receives input signals from other neurons connected to it. Each input signal corresponds to a weight, and the weighted sum of all received signals determines the activation state of the neuron. These neurons have local memory and can perform local operations. Each neuron has a single output connection, which can be branched into several parallel connections as needed to output the same signal. The signal is not affected by the number of parallel connections.

4. The intelligent construction control method for jet grouting piles based on geological information inversion as described in claim 1, characterized in that, The optimal construction parameter database consists of jet grouting pile construction parameters obtained from a cloud platform under typical geological conditions, including mud mix ratio, mud volume, grouting pressure and grouting speed, as well as drilling speed, drill rod lifting speed and jet grouting pipe rotation speed.

5. The intelligent construction control method for jet grouting piles based on geological information inversion as described in claim 1, characterized in that, The variable frequency speed and pressure regulating equipment includes a drilling drive motor and a high-pressure variable frequency pump. The drilling drive motor controls the drilling speed, the drilling rod lifting speed, and the rotation speed of the jet grouting pipe, while the high-pressure variable frequency pump controls the grouting pressure and the grouting speed.

6. The intelligent construction control method for jet grouting piles based on geological information inversion as described in claim 1, characterized in that, The method for obtaining the construction data during the drilling process is as follows: Install a torque sensor and a pore water pressure sensor on the drill bit, install an axial force sensor on the lower part of the drill rod, and complete the calibration of the sensors. Move the high-pressure jet grouting drill to the designated location, align the drill bit with the center of the hole, and level the drill to ensure it is stable and horizontal. Drilling is performed at a designated location, and the drilling depth and output power of the drilling machine are monitored in real time using a high-pressure jet grouting drill. Torque sensors, pore water pressure sensors, and axial force sensors are used to sense the torque, pore water pressure, and axial force during the drilling process in real time.

7. An intelligent construction control system for jet grouting piles based on geological information inversion, characterized in that, include: The construction process self-sensing module is used to acquire construction data during the drilling process; The real-time formation information inversion module is used to combine drilling process data and XGBoost machine learning model to perform inversion and obtain formation inversion data. The construction parameter self-matching module is used to obtain the optimal combination of construction parameters based on the formation inversion data and the self-learning parameter matching model, and based on the optimal construction parameter database. The construction process of the self-learning parameter matching model includes: using an artificial neural network to implicitly express the mapping relationship, taking construction parameters and pile quality data as samples, inputting them into the constructed neural network for training, finding the nonlinear mapping relationship between jet grouting pile construction parameters and pile quality and efficiency, storing this nonlinear mapping relationship on the connection weights of input and output neurons, taking jet grouting pile construction parameters as input and pile quality as output, and obtaining the optimal combination of construction parameters through algorithm matching; The intelligent control system links the intelligent adjustment module for construction parameters with the self-learning parameter matching model. When the inversion data of the stratum changes, the self-learning parameter matching model updates in real time to obtain the updated optimal combination of construction parameters. The intelligent adjustment module for construction parameters automatically adjusts the construction parameters by controlling the variable frequency speed and pressure regulating equipment according to the updated optimal combination of construction parameters, so that the entire construction process of the jet grouting pile is carried out according to the optimal construction parameters.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the intelligent construction control method for jet grouting piles based on stratum information inversion as described in any one of claims 1-6.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the intelligent construction control method for jet grouting piles based on stratum information inversion as described in any one of claims 1-6.

Images