Intelligent construction control method, apparatus and system for mixing pile with split-grouting

Patent metadata

Field	Value
Publication number	US-12454800-B2
Application number	US-202418743175-A
Country	US
Kind code	B2
Filing date	Jun 14, 2024
Priority date	Jan 8, 2024
Publication date	Oct 28, 2025
Grant date	Oct 28, 2025

Abstract

The present invention provides an intelligent construction control method, apparatus, and system for splitting jet grouting mixing piles, relating to geotechnical engineering. The method includes receiving real-time perception information from a construction information self-perception system, which includes drilling depth, drilling rig output power, drill bit torque, drill rod axial force, and pore water pressure of the drill bit. This information is input into a trained machine-learning model for stratum information, establishing a nonlinear implicit correspondence relationship between the perception information and construction stratum conditions, and outputting real-time stratum state information. The real-time stratum state information is then input into a trained self-matching machine-learning model for optimal construction parameters, establishing a nonlinear implicit correspondence relationship between the stratum state information and optimal construction parameters, and outputting current optimal construction parameters. This invention enables real-time intelligent inversion of stratum information and dynamic self-optimization control of construction parameters.

First claim

What is claimed is:

1 . An intelligent construction control method for splitting jet grouting mixing piles, comprising the following steps:
receiving real-time perception information from a construction information self-perception system, wherein the real-time perception information comprises drilling depth, output power of a drilling rig, torque of a drill bit, axial force of a drill rod and pore water pressure of the drill bit; inputting the real-time perception information into the trained machine-learning model for stratum information, establishing a nonlinear implicit correspondence between the real-time perception information and construction stratum conditions, and then outputting real-time stratum state information; and inputting the real-time stratum state information into the trained self-matching machine-learning model for optimal construction parameters, establishing a nonlinear implicit correspondence between the real-time stratum state information and optimal construction parameters, and then outputting current optimal construction parameters; specific details are as follows:
1) data preprocessing: removing data outliers based on a statistical analysis method, and using a regression interpolation method to fill local sparse data;
2) Feature selection and standardization: evaluating a correlation degree between features and target variables using a chi-square test method, and selecting five features with a highest correlation degree, and converting selected five features to a normal distribution with a mean value of 0 and a variance of 1 using a Z-score standardization method, to make them comparable;
3) Data division: dividing a database into n datasets with approximate sizes using a K-fold cross validation method;
4) User-defined kernel function: using a user-defined polynomial kernel function to map the data to a high-dimensional feature space, therefore transferring nonlinear problems to linear problems;
5) model training and evaluating: performing K-round training to evaluate on the built construction parameter self-matching model, where n−1 datasets in each round are used for training, and remaining datasets are used as a test set, and finally calculating the average value among K-round evaluation results as a performance index of the model, and performing next round of training if not meet the requirement;
6) optimal construction parameters prediction: inputting real-time stratum state information into a trained self-matching machine-learning model for optimal construction parameters, and obtaining predicted optimal construction parameters through forward propagation;
the self-matching machine-learning model for optimal construction parameters is a specially designed SVM class model, a kernel function of the model is the user-defined polynomial kernel function.

2 . The intelligent construction control method for splitting jet grouting mixing piles according to claim 1 , wherein the drilling depth and the output power of the drilling rig are obtained from the drilling rig; and data of the torque of the drill bit, the axial force of the drill rod and the pore water pressure of the drill bit are obtained from a torque sensor, an axial force sensor and a pore water pressure sensor.

3 . The intelligent construction control method for splitting jet grouting mixing piles according to claim 1 , wherein training the machine-learning model for stratum information specifically comprises:
building a random forest-DBSCAN integration model; obtaining existing geological state information and experimental data, and labeling the stratum state information corresponding to the drilling depth in a classification manner; inputting the experimental data and the labeled stratum state information into the random forest-DBSCAN integration model, and clustering the experimental data using a DBSCAN algorithm to train a random forest model; evaluating and optimizing the model using a validation set or a cross validation method to obtain the trained machine-learning model for stratum information, namely the trained random forest-DBSCAN integration model; and inputting the real-time perception information into the trained random forest-DBSCAN integration model to obtain an estimated value of the real-time stratum state information.

4 . The intelligent construction control method for splitting jet grouting mixing piles according to claim 1 , wherein the self-matching machine-learning model for optimal construction parameters is expressed as a mapping between multi-input and multi-output:
f:G=f ( s )
where s is an input vector (i.e., stratum condition), s=(α 1 , α 2 , . . . α n ) and α 1 -α n represents real-time stratum state information components; and G is an output vector (i.e., optimal construction parameter combination), G=(β 1 , β 2 , . . . β n ) and β 1 -β n represents output components.

5 . The intelligent construction control method for splitting jet grouting mixing piles according to claim 1 , wherein the optimal construction parameter database is the splitting pile construction parameters, comprising water-cement ratio, mud dosage, grouting pressure, grouting speed, drilling speed, lifting speed of the drill rod and rotating speed of a fan blade, obtained from the cloud platform under typical stratum conditions.

6 . The intelligent construction control method for splitting jet grouting mixing piles according to claim 1 , wherein further comprising: inputting the current matched optimal construction parameters into a construction parameter intelligent adjustment system, and dynamically adjusting the construction parameters to achieve intelligent control of a construction process.

7 . An intelligent construction apparatus for splitting jet grouting mixing piles, the intelligent construction apparatus is used to implement the steps of the intelligent construction control method for splitting jet grouting mixing piles according to claim 1 , wherein comprising a construction information self-perception system, a control apparatus, and a construction parameter intelligent adjustment system,
the construction information self-perception system comprises a drilling rig and multi-source sensing components, the drilling rig is used for detecting drilling depth and output power of the drilling rig; and the multi-source sensing components are used for acquiring data of torque of a drill bit, axial force of a drill rod and pore water pressure of the drill bit; the control apparatus is used for predicting, outputting, and displaying the real-time stratum state information based on detections from the construction information self-perception system, and then outputting current optimal construction parameters based on the real-time stratum state information; and the construction parameter intelligent adjustment system is used for real-time controlling to a variable-frequency and variable-speed pressure adjusting device based on the current optimal construction parameters.

8 . The intelligent construction apparatus for splitting jet grouting mixing piles according to claim 7 , wherein the multi-source sensing components comprise a torque sensor and a pore water pressure sensor which are mounted at the drill bit, and an axial force sensor mounted at the bottom of the drill rod; the variable-frequency and variable-speed pressure adjusting device comprises a drilling driving motor and a high voltage variable frequency pump, wherein the drilling driving motor is used for controlling drilling speed, lifting speed of the drill rod and rotating speed of a fan blade; and the high voltage variable frequency pump is used for controlling grouting pressure and grouting speed.

9 . An intelligent construction control system for

Assignees

• Univ Shandong
• Shandong Hi Speed Group Co Ltd

Inventors

• Zhuang Peizhi
• Ma Chuanyi
• Liu Mingpeng
• Zhang Jialiang
• Zhang Ning
• Qian Yuanshun
• Li Chaoji
• Zhang Shengtao
• Wang Kangxu
• Song Xiuguang
• Li Haoxiang

Classifications

• E02D15/04

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

• E02D7/24

  Placing by using fluid jets {(prefabricated concrete piles with arrangements therefor E02D5/32)} · CPC title

• E02D5/46

  making in situ by forcing bonding agents into gravel fillings or the soil (consolidating soil in general E02D3/12) · CPC title

• E02D3/12

  Consolidating by placing solidifying or pore-filling substances in the soil (making piles E02D5/46; soil-conditioning or soil-stabilising materials C09K17/00; consolidation of ground around boreholes or wells E21B43/025) · CPC title

• G06N20/20

  Ensemble learning · CPC title