CN-122013822-A - Intelligent grouting decision-making method for urban underground space pipe gallery settlement control

CN122013822ACN 122013822 ACN122013822 ACN 122013822ACN-122013822-A

Abstract

The invention discloses an intelligent grouting decision-making method for urban underground space pipe gallery settlement control, which relates to the field of underground structure health monitoring, and comprises the following steps of carrying out real-time data acquisition and fusion processing on a multi-source sensor array on a key structure node of a target pipe gallery to obtain a pipe gallery health multidimensional sensing data set; the method comprises the steps of carrying out sedimentation risk analysis processing on a piping lane health multidimensional sensing data set based on time sequence prediction and causal reasoning to obtain decision support information, carrying out grouting parameter dynamic optimization processing on the decision support information and the piping lane health multidimensional sensing data set to obtain an optimal grouting strategy, and sending the optimal grouting strategy to a grouting equipment control system to drive grouting equipment to execute automatic grouting operation. The technical problem that the grouting strategy can not be accurately adjusted in real time according to actual conditions in the conventional grouting decision for controlling the settlement of the pipe gallery in the urban underground space is solved, and the technical effects of improving the accuracy and timeliness of grouting operation and effectively controlling the settlement of the pipe gallery are achieved.

Inventors

LI QUANMING
GENG CHAO
ZHANG HAITAO
ZHANG MEICONG
ZHANG HONG
WANG YUKAI
CHEN CHENG
LI WEI

Assignees

北方工业大学
中铁第四勘察设计院集团有限公司
中国市政工程中南设计研究总院有限公司

Dates

Publication Date: 20260512
Application Date: 20251203

Claims (8)

1. An intelligent grouting decision-making method for urban underground space pipe gallery settlement control is characterized by comprising the following steps: carrying out real-time data acquisition and fusion processing on a multi-source sensor array on a key structure node of a target pipe gallery to obtain a pipe gallery health multi-dimensional sensing data set; Performing sedimentation risk analysis processing based on time sequence prediction and causal reasoning on the pipe gallery health multidimensional sensing dataset to obtain decision support information; Performing grouting parameter dynamic optimization processing on the decision support information and the pipe gallery health multidimensional sensing data set to obtain an optimal grouting strategy; And sending the optimal grouting strategy to a grouting equipment control system, and driving grouting equipment to execute automatic grouting operation.
2. The intelligent grouting decision-making method for urban underground space pipe gallery settlement control according to claim 1, wherein determining the target pipe gallery key structure node comprises: Acquiring an engineering design drawing and a geological survey report of a target pipe gallery, and constructing a pipe gallery-soil body interaction finite element model; Applying a pipe gallery dead weight load, a design traffic load and a peripheral additional load to the pipe gallery-soil body interaction finite element model, and performing statics settlement simulation calculation to obtain a first displacement cloud picture of a pipe gallery structure; Carrying out reduction correction on soil mechanical parameters of corresponding positions in the pipe gallery-soil interaction finite element model based on the space coordinates of the soil soft region identified by the geological survey report, and carrying out sedimentation simulation calculation again on the basis of the first displacement cloud image to obtain a second displacement cloud image; And fusing the first displacement cloud image and the second displacement cloud image, extracting a pipe gallery risk area with the displacement larger than a first preset threshold value or the displacement gradient larger than a second preset threshold value, and determining the central point and the boundary point of the pipe gallery risk area as the key structure node.
3. The intelligent grouting decision-making method for urban underground space pipe gallery settlement control according to claim 1, wherein the settlement risk analysis processing based on time sequence prediction and causal reasoning is performed on the pipe gallery health multidimensional sensing dataset to obtain decision support information, and the method comprises the following steps: preprocessing the pipe gallery health multidimensional sensing data set to construct a pipe gallery multivariate time sequence matrix; predicting the settlement of the pipe gallery according to the pipe gallery multivariate time sequence matrix to obtain a settlement prediction result; Carrying out causal reasoning according to the pipe gallery multivariate time sequence matrix to obtain a key sedimentation factor set; and fusing the settlement quantity prediction result with the key settlement factor set to generate decision support information.
4. The intelligent grouting decision-making method for urban underground space pipe gallery settlement control according to claim 3, wherein the pipe gallery settlement amount prediction is performed according to the pipe gallery multivariate time series matrix to obtain a settlement amount prediction result, and the method comprises the following steps: Taking each sensor node in the pipe gallery multivariate time sequence matrix as a graph node, and constructing a sensor graph adjacency matrix according to the physical connection relation of the pipe gallery structure; And predicting the settlement of the pipe gallery by adopting a space-time diagram convolution network, wherein: the encoder captures the spatial dependence and the time dynamics through a space-time convolution module according to the sensor map adjacency matrix and the pipe gallery multivariate time sequence matrix, and generates pipe gallery space-time characteristic vectors; And the decoder carries out autoregressive prediction through a time convolution layer according to the pipe gallery space-time characteristic vector, and outputs settlement amount predicted values and confidence intervals of a plurality of time steps in the future as settlement amount predicted results.
5. The intelligent grouting decision-making method for urban underground space pipe gallery settlement control according to claim 3, wherein the causal reasoning is carried out according to the pipe gallery multivariate time sequence matrix to obtain a key settlement factor set, comprising: Performing condition independence test on all variables in the pipe gallery multivariate time sequence matrix, and constructing an undirected causal skeleton diagram; Identifying a V-structure in the undirected causal skeleton graph, and orienting a corresponding causal arrow according to an identification result to obtain a part of directed acyclic graph; based on a time priority principle and priori knowledge of pipe gallery structural mechanics, orienting the rest undirected arrows in the part of directed acyclic graphs to obtain directed causal graphs; and extracting all father nodes directly pointing to the settling volume nodes from the directed causal graph to form a key settling factor set.
6. The intelligent grouting decision-making method for urban underground space pipe gallery settlement control according to claim 2, wherein the decision-support information and the pipe gallery health multidimensional sensing dataset are subjected to grouting parameter dynamic optimization processing to obtain an optimal grouting strategy, and the method comprises the following steps: Defining the decision support information and the piping lane health multi-dimensional perception dataset as a state space; defining grouting pressure, grouting flow, slurry water-cement ratio and three-dimensional coordinates of a grouting hole as action spaces; Defining a reward function according to the sedimentation recovery value, the accumulated grouting quantity and the pressure fluctuation variance; and carrying out dynamic optimization processing on grouting parameters according to the state space, the action space and the reward function to obtain an optimal grouting strategy.
7. The intelligent grouting decision-making method for urban underground space pipe gallery settlement control according to claim 6, wherein the dynamic optimization processing of grouting parameters is performed according to the state space, the action space and the reward function, so as to obtain an optimal grouting strategy, and the method comprises the following steps: Constructing a simulation environment based on the pipe gallery-soil body interaction finite element model, and training the grouting intelligent body until training is completed by adopting a near-end strategy optimization algorithm according to the state space, the action space and the reward function; And inputting the real-time state space into the trained grouting intelligent body, and outputting an optimal grouting parameter value by the grouting intelligent body to form the optimal grouting strategy.
8. The intelligent grouting decision-making method for urban underground space pipe gallery settlement control according to claim 1, wherein the optimal grouting strategy is sent to a grouting equipment control system to drive and execute automatic grouting operation, and the method comprises the following steps: Acquiring a latest pipe gallery health multidimensional sensing data set at preset time intervals; Acquiring an updated optimal grouting strategy according to the latest pipe gallery health multidimensional sensing data set; and dynamically adjusting the optimal grouting strategy which is executing automatic grouting operation according to the updated optimal grouting strategy.

Description

Intelligent grouting decision-making method for urban underground space pipe gallery settlement control Technical Field The application relates to the field of underground structure health monitoring, in particular to an intelligent grouting decision method for urban underground space pipe gallery settlement control. Background Urban underground space pipe gallery is taken as an important component of urban infrastructure, the safe and stable operation of the urban underground space pipe gallery directly relates to the normal operation of cities and the life quality of residents, and the problem of pipe gallery settlement seriously threatens the structural safety of the pipe gallery, so that the normal operation of various pipelines borne by the pipe gallery is influenced, and therefore, the effective control of pipe gallery settlement is important. At present, the main method for solving the problem of settlement control of the pipe gallery in the urban underground space is to perform regular grouting maintenance based on preset grouting parameters, and prevent or slow down settlement by reinforcing soil around the pipe gallery. However, the current method mainly depends on fixed grouting parameters and a regular maintenance mode, so that the grouting strategy is difficult to adjust in real time according to the actual sedimentation condition of a pipe gallery and the dynamic change of the surrounding environment, and the problem that the grouting operation lacks accuracy and timeliness and resources are wasted due to excessive grouting or sedimentation cannot be effectively controlled due to insufficient grouting is caused. In the related art at the present stage, the grouting decision for controlling the settlement of the pipe gallery of the urban underground space has the technical problem that the grouting strategy cannot be accurately adjusted in real time according to the actual situation. Disclosure of Invention According to the intelligent grouting decision method for urban underground space pipe gallery settlement control, the data of the multisource sensor array on the key structure node of the target pipe gallery are collected and fused in real time, the healthy multidimensional sensing data set is obtained, the settlement risk analysis of time sequence prediction and causal reasoning is carried out on the data set, decision support information is obtained, grouting parameters are dynamically optimized by combining the decision support information and the data set, an optimal grouting strategy is obtained, the strategy is sent to a grouting equipment control system, automatic grouting operation is driven and other technical means, the technical problem that the grouting strategy cannot be accurately adjusted in real time according to actual conditions in the conventional grouting decision for urban underground space pipe gallery settlement control is solved, and the technical effects of improving the accuracy and timeliness of grouting operation and effectively controlling pipe gallery settlement are achieved. The application provides an intelligent grouting decision-making method for urban underground space pipe gallery settlement control, which comprises the steps of carrying out real-time data acquisition and fusion processing on a multi-source sensor array on a key structure node of a target pipe gallery to obtain a pipe gallery health multi-dimensional sensing data set, carrying out settlement risk analysis processing on the pipe gallery health multi-dimensional sensing data set based on time sequence prediction and causal reasoning to obtain decision support information, carrying out grouting parameter dynamic optimization processing on the decision support information and the pipe gallery health multi-dimensional sensing data set to obtain an optimal grouting strategy, and sending the optimal grouting strategy to a grouting equipment control system to drive grouting equipment to execute automatic grouting operation. In a possible implementation mode, a target pipe gallery key structure node is determined, the following processing is carried out, an engineering design drawing and a geological survey report of the target pipe gallery are obtained, a pipe gallery-soil body interaction finite element model is constructed, pipe gallery dead weight load, design passing load and peripheral additional load are applied to the pipe gallery-soil body interaction finite element model, static settlement simulation calculation is carried out, a first displacement cloud picture of the pipe gallery structure is obtained, reduction correction is carried out on soil body mechanical parameters at corresponding positions in the pipe gallery-soil body interaction finite element model based on space coordinates of a soil weak area identified by the geological survey report, settlement simulation calculation is carried out again on the basis of the first displacement cloud picture, a second displacement cloud p