US 12,462,482 B1
Digital twin-based intelligent slope monitoring methods, systems, and storage media
Jinglai Sun, Beijing (CN); Hao Liu, Beijing (CN); Jun Yuan, Beijing (CN); Xinling Wang, Beijing (CN); Xun Xi, Beijing (CN); Yue Su, Beijing (CN); Hui Fang, Beijing (CN); Yang Zhou, Beijing (CN); Liwen Dong, Beijing (CN); Yafei Bai, Beijing (CN); and Shengtao Shi, Beijing (CN)
Assigned to BEIJING MUNICIPAL ENGINEERING RESEARCH INSTITUTE, Beijing (CN)
Filed by BEIJING MUNICIPAL ENGINEERING RESEARCH INSTITUTE, Beijing (CN)
Filed on Jul. 1, 2025, as Appl. No. 19/257,429.
Claims priority of application No. 202510073584.3 (CN), filed on Jan. 17, 2025.
Int. Cl. G06T 17/00 (2006.01)
CPC G06T 17/00 (2013.01) 8 Claims
OG exemplary drawing
 
1. A digital twin-based intelligent slope monitoring method, comprising:
obtaining first point cloud data of a surface of a slope at a past preset time point and creating a digital twin model based on the first point cloud data;
obtaining second point cloud data of the surface of the slope at a current time point, transforming the first point cloud data, the second point cloud data, and the digital twin model into a same coordinate system, performing, based on a preset size, a grid division on the digital twin model to generate a plurality of first grids, defining a duration between the past preset time point and the current time point as a target duration, calculating a displacement change value of each first grid among the plurality of first grids during the target duration, and displaying the displacement change value in the digital twin model;
defining the first grid with a displacement change value greater than a first threshold as a first region, obtaining an actual rainfall in the first region during the target duration, establishing a first coordinate system with time as a horizontal axis and the actual rainfall as a vertical axis, plotting a first change curve of the actual rainfall over time in the first coordinate system, obtaining one or more extreme points of the first change curve, for each extreme point, defining a time point corresponding to the extreme point as a first time point, and dividing the target duration into a plurality of first durations with different lengths based on the one or more first time points corresponding to the one or more extreme points;
for each first duration of the plurality of first durations, setting a plurality of rainfall patterns, each rainfall pattern corresponding to a plurality of pieces of historical rainfall data, determining a rainfall pattern from the plurality of rainfall patterns as an optimal pattern based on the actual rainfall during the first duration, obtaining an optimal time point within the first duration based on the optimal pattern and the plurality of pieces of historical rainfall data, designating the actual rainfall at the optimal time point as a representative rainfall during the first duration, constructing a prediction model based on the historical rainfall data corresponding to the plurality of first durations, predicting an optimal pattern and a representative rainfall for a future duration based on the optimal pattern and representative rainfall of the first duration, and defining the representative rainfall during the future duration as a predicted rainfall; and
obtaining a historical rainfall during the target duration, obtaining a first pore water pressure distribution of soil in the first region based on the historical rainfall, generating a first safety factor of the first region during the future duration based on the predicted rainfall and the first pore water pressure distribution, designating an average of all first safety factors of the slope as a final safety factor of the slope, and displaying the final safety factor of the slope in the digital twin model.