CN-121998241-A - Comprehensive evaluation and emergency treatment system and method for post-disaster stack of underground engineering

CN121998241ACN 121998241 ACN121998241 ACN 121998241ACN-121998241-A

Abstract

The invention discloses a comprehensive evaluation and emergency treatment system and method for post-disaster accumulation bodies of underground engineering, wherein the method comprises the following steps: and pre-storing a geological database by means of a tunnel site edge computing terminal, acquiring multi-source data such as three-dimensional point cloud, images, water pressure, surrounding rock deformation and the like in real time, acquiring key parameters through preprocessing and convolutional neural network identification, generating a mechanism parameter set by fusing formation factor information, driving a numerical simulation engine to complete fluid-solid coupling calculation, and automatically generating and issuing equipment control instructions after assessing instability risks. The invention realizes the full-chain cooperation of 'perception-modeling-simulation-threshold triggering-execution' of the post-disaster accumulation body, greatly improves the systematicness and the integrity of emergency treatment, and effectively ensures the overall effect of post-disaster emergency of underground engineering.

Inventors

LI KUN
LI ZHUOYU
ZHANG XIAOBAO
YANG WEIQIANG
Si Fuan
DUAN SHIWEI
HUANG ZHIYI
XU JIANGBO
WU XIONG
ZHANG JIAJUN
WANG SHAOWEI
SUN WEN

Assignees

水利部水利水电规划设计总院
长安大学

Dates

Publication Date: 20260508
Application Date: 20260115

Claims (10)

1. The method for comprehensively evaluating and emergency disposing the post-disaster stack of the underground engineering is characterized by comprising the following steps of: The method comprises the steps of obtaining stratum cause information of a tunnel on a node to be monitored to generate a geological database (21), pre-storing the stratum cause information to an edge computing terminal deployed on a tunnel site, automatically executing an emergency treatment process by the edge computing terminal according to a set control program, wherein the emergency treatment process is set as follows: acquiring at least one of three-dimensional point cloud data, field image data, water pressure data and surrounding rock deformation data of a position to be acquired of a post-disaster accumulation body in real time; preprocessing at least one group of obtained three-dimensional point cloud data to construct a local coordinate system, and calculating geometric form parameters of a part to be acquired of the post-disaster accumulation body by utilizing the preprocessed three-dimensional point cloud data in the local coordinate system; Inputting the acquired field image data into a pre-trained convolutional neural network model, wherein the pre-trained convolutional neural network model is configured to acquire a probability value corresponding to each material category according to the input field image data, and determine the material category with the largest probability value as a material composition parameter of a part to be acquired of a post-disaster accumulation body to output; Invoking a geological database (21) pre-stored in the edge computing terminal, reading stratum cause information of a tunnel corresponding to mileage of a position to be collected of a post-disaster accumulation body, and combining the geometric form parameter and the material composition parameter to generate a mechanism parameter set representing a disaster formation mechanism; Automatically generating a simulation configuration parameter set based on the mechanism parameter set to drive a numerical simulation engine to construct a stack numerical model, and calculating fluid-solid coupling numerical values of the stack numerical model to obtain distribution characteristics of a displacement field, a stress field and a seepage field of a position to be collected of the stack after disaster; Extracting key physical quantities from the distribution characteristics of a displacement field, a stress field and a seepage field of a position to be collected of the post-disaster accumulation body, and comparing the key physical quantities with a preset physical threshold condition to generate a destabilization mode parameter and a risk degree parameter with association relations so as to represent the destabilization characteristics of the accumulation body; And automatically generating control instruction parameters of corresponding equipment according to the destabilizing mode parameters and the risk degree parameters, and issuing the control instruction parameters to the corresponding equipment through a communication interface so as to drive the corresponding equipment to execute corresponding emergency measures.
2. The method for comprehensively evaluating and disposing post-disaster piles of underground engineering according to claim 1, wherein the method for preprocessing the three-dimensional point cloud data comprises the following steps: And carrying out statistical filtering and multi-station registration processing on the acquired three-dimensional point cloud data.
3. The post-disaster stack comprehensive evaluation and emergency treatment method of underground engineering according to claim 1, wherein the simulation configuration parameter set at least comprises geometric model parameters, material constitutive model selection parameters and boundary load configuration parameters.
4. The method for comprehensively evaluating and handling post-disaster piles of underground engineering according to claim 1, wherein the simulation configuration parameter set is set as an input interface parameter of the numerical simulation engine and is used for triggering the numerical simulation engine to call corresponding material constitutive model data, boundary loads and initial conditions related to disaster causes and construction constraint parameters of the numerical pile model from a preset configuration file.
5. The post-disaster stack comprehensive evaluation and emergency treatment method for underground works of claim 4, wherein the construction constraint parameters of the stack numerical model comprise at least one of calculation step size, convergence criterion and safety coefficient.
6. The post-disaster stack comprehensive evaluation and emergency treatment method of underground engineering according to claim 1, wherein a geometric modeling mode of the stack numerical model is selected based on a determination result of the geometric form parameter, and the determination result of the geometric form parameter comprises: Determining at least one of a partition mode of an initial geometric model of the stack, determining grid types or grid densities of different areas, and determining positions and ranges of contact surfaces, slip surfaces or weak surfaces in the simulation model.
7. The post-disaster stack comprehensive evaluation and emergency treatment method of underground engineering according to claim 1, wherein at least one of a reduction coefficient of a material constitutive model selection parameter in the stack numerical model, a loading amplitude or loading rate of a boundary load configuration parameter, and a safety coefficient or a stability criterion threshold in a simulation calculation process is calibrated in real time according to the risk degree parameter.
8. The method for comprehensively evaluating and handling post-disaster piles of underground works according to claim 1, wherein when the measured water pressure value in the water pressure data of the position to be collected of the post-disaster piles and/or the measured deformation rate in the surrounding rock deformation data exceed a preset physical threshold, a correction mechanism is automatically triggered, and the correction mechanism is configured to dynamically adjust the permeation-related parameters or the rheological-related parameters of the simulation configuration parameter set according to the risk degree parameters.
9. The post-disaster stack comprehensive evaluation and emergency treatment method for underground works according to claim 1, wherein the control instruction parameters of the equipment include: at least one of control signals for controlling the operation permission state of the slag removing machine, the start-stop state of grouting equipment and the triggering state of the audible and visual alarm device.
10. A post-disaster stack comprehensive evaluation and emergency disposal system for underground works for implementing the method of any one of claims 1 to 9, characterized in that the system comprises: The system comprises a data acquisition unit (1), wherein the data acquisition unit (1) is configured to acquire at least one of three-dimensional point cloud data, field image data, water pressure data and surrounding rock deformation data of a position to be acquired of a post-disaster accumulation body in real time; An edge calculation unit (2) connected to the data acquisition unit (1), wherein the edge calculation unit (2) comprises a geological database (21), a point cloud processing module (22), a material identification module (23), a mechanism parameter generation module (24), a simulation configuration parameter generation module (25) and a multi-field coupling simulation module (26), the geological database (21) is configured to internally store stratum cause information of a tunnel on a monitoring node, the point cloud processing module (22) is configured to pre-process at least one group of acquired three-dimensional point cloud data to construct a local coordinate system, and calculate geometrical shape parameters of a to-be-acquired position of the post-disaster pile-up body by using the pre-processed three-dimensional point cloud data in the local coordinate system, the material identification module (23) is configured to input the acquired on-site image data into a pre-trained convolutional neural network model, the pre-trained convolutional neural network model is configured to acquire probability values corresponding to each material class according to the input on-site image data, and store the probability values therein as the most likely to the post-disaster-pile-up body data, the geometrical shape parameters of the post-disaster-pile-up body to be-acquired position are calculated by the geometrical shape parameters of the post-disaster-pile-up body to be-up body (24) in combination with the pre-processed three-dimensional point cloud data in the local coordinate system, the simulation configuration parameter generation module (25) is configured to automatically generate a simulation configuration parameter set based on the mechanism parameter set, the multi-field coupling simulation module (26) is configured to input the simulation configuration parameter set to drive a numerical simulation engine to construct a stack numerical model, calculate fluid-solid coupling numerical values of the stack numerical model, obtain distribution characteristics of a displacement field, a stress field and a seepage field of a position to be collected of the stack after the disaster, extract key physical quantities from the distribution characteristics of the displacement field, the stress field and the seepage field of the position to be collected of the stack after the disaster, compare the key physical quantities with preset physical threshold conditions, and generate a destabilization mode parameter and a risk degree parameter with association relation to represent the destabilization characteristics of the stack; The control execution unit (3) comprises a programmable logic controller and an execution mechanism driving module (32), wherein the programmable logic controller is configured to automatically generate control instruction parameters of corresponding equipment according to the instability mode parameters and the risk degree parameters, and the execution mechanism driving module (32) is configured to receive the control instruction parameters issued by the programmable logic controller to control the corresponding equipment so as to execute corresponding emergency measures; -a communication unit (4) for establishing a communication link between the edge calculation unit (2) and the control execution unit (3) via an industrial ethernet or wireless communication module.

Description

Comprehensive evaluation and emergency treatment system and method for post-disaster stack of underground engineering Technical Field The invention relates to the technical field of emergency disposal and intelligent monitoring of underground engineering disasters, in particular to a system and a method for comprehensively evaluating and emergency disposal of post-disaster accumulation bodies of underground engineering. Background In the tunnel construction or operation process, the tunnel is influenced by high ground stress, fault fracture zones, water-rich stratum, soft rock creep, rock structural surface degradation and other factors, surrounding rock instability, support damage, water bursting and mud burst and other disasters easily occur, and a pile body is formed after the disasters and can be deformed continuously, seepage developed or subjected to secondary instability. The existing emergency treatment generally depends on manual investigation and experience judgment, and has the following technical problems: 1) The site information is difficult to objectively quantify, the morphology, pore structure, seepage and material composition of the stacked body are mostly dependent on visual inspection or local sampling, and repeatable three-dimensional geometric and physical parameters are difficult to obtain under the environment with low visibility, high humidity and high risk, so that key characteristics (such as local seepage concentration, laminar weak surfaces and plastic folds) are missed. 2) The modeling and analysis chain is not closed loop, although the technology introduces three-dimensional laser scanning, photogrammetry or numerical simulation, the scanning data are mostly used for visual display, a computable geometric model is difficult to automatically generate, a substance identification result often stays on an information layer, automatic configuration of material constitutive parameters and boundary conditions is not formed, manual conversion is still relied on between numerical analysis and on-site treatment, and efficiency and consistency are insufficient. 3) The engineering disposal response is not timely, the time for issuing the disposal instruction from investigation and consultation is long, the post-disaster accumulation body can continue to permeate or deform in the waiting period, the secondary instability probability is increased, and the safety of personnel and equipment is threatened. In tunnel environments in particular, mechanical equipment entitlement control and personnel evacuation triggering require reliable field signaling and automation interface support. Therefore, a technical scheme based on multi-source physical measurement, with automatic numerical modeling and multi-field coupling simulation as cores and with equipment control signal output as a landing point is needed, so that integrated closed loop of post-disaster accumulation body 'perception-modeling-simulation-threshold triggering-execution' is realized, and timeliness and safety of emergency treatment are improved. Disclosure of Invention Accordingly, the present invention is directed to a system and a method for comprehensive evaluation and emergency treatment of post-disaster accumulation bodies in underground engineering, which solve the technical problems mentioned in the prior art. The method for comprehensively evaluating and emergency disposing the post-disaster stack of the underground engineering comprises the following steps: The method comprises the steps of obtaining stratum cause information of a tunnel on a node to be monitored to generate a geological database, pre-storing the stratum cause information into an edge computing terminal deployed on a tunnel site, automatically executing an emergency treatment process by the edge computing terminal according to a set control program, wherein the emergency treatment process is set as follows: acquiring at least one of three-dimensional point cloud data, field image data, water pressure data and surrounding rock deformation data of a position to be acquired of a post-disaster accumulation body in real time; preprocessing at least one group of obtained three-dimensional point cloud data to construct a local coordinate system, and calculating geometric form parameters of a part to be acquired of the post-disaster accumulation body by utilizing the preprocessed three-dimensional point cloud data in the local coordinate system; Inputting the acquired field image data into a pre-trained convolutional neural network model, wherein the pre-trained convolutional neural network model is configured to acquire a probability value corresponding to each material category according to the input field image data, and determine the material category with the largest probability value as a material composition parameter of a part to be acquired of a post-disaster accumulation body to output; Invoking a geological database pre-stored in the edge computing termin