Intelligent construction control method and system for jet grouting pile based on stratum information inversion

Patent metadata

Field	Value
Publication number	US-12559897-B2
Application number	US-202418764170-A
Country	US
Kind code	B2
Filing date	Jul 4, 2024
Priority date	Sep 15, 2023
Publication date	Feb 24, 2026
Grant date	Feb 24, 2026

Abstract

The present invention relates to pile foundations and provides an intelligent construction control method and system for jet grouting piles based on stratum information inversion. This method integrates multi-source sensing components and local transmission to perceive real-time drilling information to a data integration terminal. Using engineering soil layer data as training samples, a machine learning algorithm correlates perception information with geological conditions, judging and outputting stratum conditions in real time. An XGBoost model quickly and accurately identifies soil layers at the site. Based on big data matching of a cloud platform, an optimal construction parameter database is established, and the optimal combination of parameters is acquired through algorithm matching. A variable-frequency and variable-speed pressure adjusting device links a piling machine intelligent control system with other subsystems to achieve intelligent control, reducing material consumption and improving pile quality and efficiency.

First claim

What is claimed is:

1 . An intelligent construction control method for a jet grouting pile based on stratum information inversion, comprising the following steps:
acquiring construction data in a drilling process; performing inversion in combination with the construction data of the drilling process and an XGBoost machine learning model to obtain stratum inversion data; obtaining an optimal construction parameter combination based on matching of an optimal construction parameter database according to the stratum inversion data and a self-learning parameter matching model; and linking a construction parameter intelligent adjustment module with the self-learning parameter matching model, wherein when the stratum inversion data changes, the self-learning parameter matching model is updated in real time to obtain an updated optimal construction parameter combination, and the construction parameter intelligent adjustment module automatically adjusts construction parameters by controlling a variable-frequency and variable-speed pressure adjusting device according to the updated optimal construction parameter combination, so that the whole construction process of the jet grouting pile is performed according to optimal construction parameters.

2 . The intelligent construction control method for a jet grouting pile based on stratum information inversion according to claim 1 , wherein the construction of the XGBoost machine learning model lies in that:
by using engineering stratum data as a training sample for training, and drilling depth, torque, axial force, pore water pressure and output power as an input layer of the model; a correspondence relationship between perception information and stratum conditions is established; and by using the soil layer type, strength, a water content and a permeability coefficient as an output layer, a stratum is predicted, and the stratum information is inverted in real time.

3 . The intelligent construction control method for a jet grouting pile based on stratum information inversion according to claim 1 , wherein a construction process of the self-learning parameter matching model comprises:
implicitly expressing a mapping relationship by using an artificial neural network; with data of the construction parameters and pile quality as samples, inputting the data into a constructed neural network for training; finding a nonlinear mapping relationship between the construction parameters of the jet grouting pile and the pile quality and efficiency; storing the nonlinear mapping relationship in a connection weight of input and output neurones; and with the construction parameters of the jet grouting pile as input variables and the pile quality as an output variable, acquiring an optimal combination of the construction parameters by algorithm matching.

4 . The intelligent construction control method for a jet grouting pile based on stratum information inversion according to claim 3 , wherein in the self-learning parameter matching model, each neuron in the neural network receives input signals of other neurones connected to the neuron, and each input signal corresponds to a weight; a weighted sum of all the received signals determines an activation state of the neuron; these neurones have local memories, and can perform local operations; and each neuron has a single output connection which is capable of being branched into a plurality of parallel connections as needed to output a same signal, and the signal is not affected by the number of the parallel connections.

5 . The intelligent construction control method for a jet grouting pile based on stratum information inversion according to claim 1 , wherein the optimal construction parameter database is jet grouting pile construction parameters, comprising a slurry ratio, mud dosage, guniting pressure, grouting speed, drilling speed, lifting speed of a drill rod and rotating speed of a jet grouting pipe, obtained on the basis of a cloud platform under typical stratum conditions.

6 . The intelligent construction control method for a jet grouting pile based on stratum information inversion according to claim 1 , wherein the variable-frequency and variable-speed pressure adjusting device comprises a drilling driving motor and a high voltage variable frequency pump, drilling speed, lifting: speed of a drill rod and rotating speed of a jet grouting pipe are controlled by the drilling driving motor; and guniting pressure and grouting speed are controlled by the high voltage variable frequency pump.

7 . The intelligent construction control method for a jet grouting pile based on stratum information inversion according to claim 1 , wherein a method for acquiring the construction data in the drilling process comprises:
mounting a torque sensor and a pore water pressure sensor on a drill bit, and an axial force sensor at a lower part of a drill rod, and labeling the sensors; moving a high-pressure jet-grouting drilling rig to a specified position, aligning the drill bit to a center of a hole, leveling the drilling rig and placing the drilling rig smoothly and horizontally; and performing drilling in the specified position, monitoring drilling depth and output power of the drilling rig in real time by using the high-pressure jet-grouting drilling rig, and perceiving torque, pore water pressure and axial force in the drilling process in real time by using the torque sensor, the pore water pressure sensor, and the axial force sensor.

8 . A computer-readable storage medium, in which a computer program is stored, wherein when the program is executed by a processor, the steps of the intelligent construction control method for a jet grouting pile based on stratum information inversion according to claim 1 is implemented.

9 . A computer device, comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein when the processor executes the program, the steps of the intelligent construction control method for a jet grouting pile based on stratum information inversion according to claim 1 is implemented.

10 . An intelligent construction control system for a jet grouting pile based on stratum information inversion, comprising:
a construction process self-perception module, used for acquiring construction data in a drilling process; a stratum information real-time inversion module, used for performing inversion in combination with the construction data of the drilling process and an XGBoost machine learning model to obtain stratum inversion data; a construction parameter self-matching module, used for obtaining an optimal construction parameter combination based on matching of an optimal construction parameter database according to the stratum inversion data and a self-learning parameter matching model; and an intelligent control construction process, used for linking a construction parameter intelligent adjustment module with the self-learning parameter matching model, wherein when the stratum inversion data changes, the self-learning parameter matching model is updated in real time to obtain an updated optimal construction parameter combination, and the construction parameter intelligent adjustment module automatically adjusts construction parameters by controlling a variable-frequency and variable-speed pressure adjusting device according to the updated optimal construction parameter combination, so that a whole construction process of the jet grouting pile is performed according to the optimal construction parameters.

Assignees

• Univ Shandong
• Univ Shandong Jianzhu

Inventors

• Zhuang Peizhi
• Wang Kangxu
• Yang He
• Yin Jingjing
• Song Xiuguang
• Li Chaoji
• Zhou Chong
• Qian Yuanshun
• Li Chao
• Liu Mingpeng

Classifications

• G06N3/08

  Learning methods · CPC title

• E21B44/00

  Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions · CPC title

• E02D2300/0018

  Cement used as binder · CPC title

• E02D2250/0023

  Cast, i.e. in situ or in a mold or other formwork · CPC title

• E02D15/04 Primary

  Placing concrete in mould-pipes, pile tubes, bore-holes or narrow shafts · CPC title