CN-122021122-A - Knowledge-graph-based vacuum preloading construction decision method and system and electronic equipment

CN122021122ACN 122021122 ACN122021122 ACN 122021122ACN-122021122-A

Abstract

The application discloses a vacuum preloading construction decision method and system based on a knowledge graph and electronic equipment, and relates to the technical field of soft soil foundation treatment. The method comprises the steps of constructing a vacuum preloading construction knowledge graph which comprises construction element entities, semantic relations and reasoning rules extracted from historical engineering data, obtaining environment parameters and design indexes of a target area, utilizing knowledge graph reasoning and matching to obtain initial construction scheme parameters, constructing a finite element model based on the initial parameters to conduct numerical simulation, correcting the parameters according to simulation results to obtain the target construction scheme parameters, and finally generating control instructions according to the target parameters to guide equipment construction. The application adopts a double decision mechanism of data-driven reasoning and physical model verification, effectively overcomes the dependence of the traditional method on manual experience, improves the accuracy and scientificity of construction parameter setting, and realizes the economical efficiency and timeliness optimization of a construction scheme.

Inventors

LIU YUE
HU KE
ZHOU LINQI
Zhao Hanchuan
ZHU JUNZHOU
LI QING
ZHANG QIN
Cen Changming
Song Dunan
HUANG XIANGPING
CAO XIONG
ZHAO HONGGANG

Assignees

珠海市规划设计研究院

Dates

Publication Date: 20260512
Application Date: 20251229

Claims (10)

1. The vacuum preloading construction decision method based on the knowledge graph is characterized by comprising the following steps of: Constructing a knowledge graph of vacuum preloading construction, wherein the knowledge graph comprises construction element entities extracted from historical engineering data, semantic relations among the construction element entities and reasoning rules obtained based on association rule mining; acquiring an environmental parameter data set and design indexes of a target area, and carrying out reasoning matching by utilizing the knowledge graph to obtain initial construction scheme parameters; Constructing a finite element model based on the initial construction scheme parameters to carry out numerical simulation, and correcting the initial construction scheme parameters according to simulation results to obtain target construction scheme parameters; and generating a control instruction for the vacuum preloading equipment according to the target construction scheme parameters so as to execute construction.
2. The knowledge-graph-based vacuum preloading construction decision method of claim 1, wherein the constructing the knowledge graph of vacuum preloading comprises: Collecting multi-source heterogeneous data, wherein the multi-source heterogeneous data comprises at least one of geological survey reports, construction scheme parameters, process monitoring data and construction specification documents of historical vacuum preloading projects; Cleaning and structuring the multi-source heterogeneous data, and extracting the construction element entity, wherein the construction element entity at least comprises geological feature data, construction equipment parameters and soil body representation system data; constructing a map structure which takes the construction element entities as nodes and takes the logical relations among the construction element entities as edges, and storing the map structure into a map database; and analyzing the map structure by using an association rule mining algorithm, and mining a strong association rule between the geological feature and the construction equipment parameter as the reasoning rule.
3. The knowledge-based vacuum preloading construction decision method of claim 2, wherein the obtaining the environmental parameter data set and the design index of the target area, performing inference matching by using the knowledge graph, and obtaining the initial construction scheme parameters comprises: calculating the similarity of the environmental parameter data set of the target area, the design index and the historical engineering case in the knowledge graph; Selecting a historical engineering case with similarity meeting a preset threshold value in the knowledge graph as a reference case; Adaptively adjusting the construction scheme parameters based on the reference case association and combining the reasoning rules to deduce the initial construction scheme parameters applicable to the target area; the initial construction scheme parameters comprise one or more of plastic drain board spacing, drain board setting depth, vacuum loading amplitude and pressure stabilizing duration.
4. The knowledge-graph-based vacuum preloading construction decision method of claim 1, wherein the constructing a finite element model based on the initial construction plan parameters to perform numerical simulation, and correcting the initial construction plan parameters according to simulation results to obtain target construction plan parameters, comprises: Inputting the initial construction scheme parameters and the environmental parameter data set into a finite element model, and calculating to obtain simulated soil body characterization system data; Judging whether the data of the simulated soil body representation system meets the design index or not; If yes, taking the initial construction scheme parameters as the target construction scheme parameters; If the parameter sensitivity model is not met, key parameter values in the initial construction scheme parameters are adjusted based on the preset parameter sensitivity model, and the finite element model is operated again to perform iterative calculation until the output simulated soil body representation system data meets the design index.
5. The knowledge-graph-based vacuum preloading construction decision method of claim 2, wherein generating control instructions for a vacuum preloading apparatus to perform construction in accordance with the target construction plan parameters, further comprises: And acquiring real-time monitoring data of a construction site, and analyzing the real-time monitoring data according to the inference rule in the knowledge graph to obtain risk early warning information and corresponding equipment inspection instructions.
6. The knowledge-graph-based vacuum preloading construction decision method of claim 5, wherein the acquiring real-time monitoring data of a construction site, analyzing the real-time monitoring data according to the inference rules in the knowledge graph to obtain risk early warning information and corresponding equipment inspection instructions, comprises: Acquiring real-time monitoring data of a construction site, wherein the real-time monitoring data comprises at least one of vacuum degree under a membrane, earth surface sedimentation rate and water yield; Mapping the real-time monitoring data to corresponding entity nodes of the knowledge graph; and if the change trend of the monitoring data triggers an abnormal threshold value, positioning an abnormal reason by combining a causal relation chain in the knowledge graph, and generating corresponding risk early warning information and equipment checking instructions.
7. The knowledge-graph-based vacuum preloading construction decision method of claim 5, wherein the acquiring real-time monitoring data of a construction site further comprises: Calculating to obtain real-time soil characterization system data by using a preset soil mechanics inversion rule based on the real-time monitoring data in a preset time interval; Comparing the real-time soil body characterization system data with the design index, and generating a rate adjustment instruction according to a comparison result; and adjusting the target construction scheme parameters according to the rate adjustment instruction.
8. The knowledge-graph-based vacuum preloading construction decision method of claim 5, further comprising: And after the construction of the target area is finished, integrating the environment parameter data set, the design index, the target construction scheme parameters and the real-time monitoring data of the target area into a new case, storing the new case into the knowledge graph, and updating the construction element entity and the reasoning rule.
9. A vacuum preloading construction decision system based on a knowledge graph is characterized by comprising: the map construction module is used for constructing and storing a vacuum preloading construction knowledge map, wherein the knowledge map comprises construction element entities and semantic relations and reasoning rules among the construction element entities; The scheme generation module is used for acquiring geological investigation parameters and design indexes of a target area to be constructed, and carrying out reasoning and matching by utilizing the knowledge graph to generate initial construction scheme parameters; The simulation verification module is used for operating the finite element model based on the initial construction scheme parameters, and correcting the initial construction scheme parameters according to a simulation result so as to determine target construction scheme parameters; The construction control module is used for outputting the target construction scheme parameters so as to guide external vacuum preloading equipment; And the monitoring analysis module is used for acquiring real-time monitoring data in the construction process and carrying out abnormal research and judgment and risk early warning by utilizing the knowledge graph.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the knowledge-graph-based vacuum preloading construction decision method as defined in any of claims 1-8 when executing the program.

Description

Knowledge-graph-based vacuum preloading construction decision method and system and electronic equipment Technical Field The application relates to the technical field of soft soil foundation treatment, in particular to a vacuum preloading construction decision method and system based on a knowledge graph and electronic equipment. Background The vacuum preloading method is used as a high-efficiency soft soil foundation reinforcement technology and is widely applied to engineering construction of ports, wharfs, yards, airport runways and the like. The principle is that a vertical plastic drainage plate is arranged in soft clay, a sand cushion layer and a sealing film are paved on the surface of the soil body, air in the sealing film is pumped by a vacuum pump to form negative pressure, and pore water in the soil body is discharged under the action of pressure difference, so that the soil body is accelerated to solidify and subside, and the bearing capacity of a foundation is improved. At present, the establishment of a vacuum preloading construction scheme mainly depends on industry standards such as building foundation treatment technical Specification and personal experience of designers. The designer typically determines the spacing, depth, and vacuum loading scheme of the plastic drain boards based on soil layer parameters in the survey report, in combination with empirical values from past similar projects. However, the decision-making mode relying on artificial experience has strong subjectivity, and for engineering with complicated geological conditions, it is often difficult to combine safety and economy. On one hand, too conservative design can lead to material waste and prolonged construction period, and on the other hand, insufficient experience can lead to unqualified reinforcement effect and even cause engineering accidents such as foundation instability. In addition, along with the promotion of infrastructure construction, massive vacuum preloading historical engineering data are accumulated, including geological survey reports, construction design drawings, on-site monitoring records and the like. But most of this data is stored in a decentralized manner in unstructured documents, forming a large number of "data islands". The existing technical means is difficult to effectively integrate and deeply mine the multi-source heterogeneous data, so that deep association rules between geological parameters and construction effects contained in historical data cannot be extracted and reused, and data support cannot be provided for decision making of new projects. While some engineering works began to introduce numerical simulation methods such as finite element analysis to aid in design, challenges are presented in practical applications. The accuracy of finite element models is highly dependent on input boundary conditions and soil structure parameters, and initial values of the parameters often lack accurate basis. If the parameter deviation of the initial scheme is large, not only the analog calculation is not converged or the time is too long, but also a conclusion contrary to the actual situation can be obtained. The existing construction decision method often breaks the connection between the historical experience data and the physical mechanics simulation, and lacks a technical means capable of organically combining the historical engineering knowledge with a numerical simulation mechanism, so that the intelligent and automatic generation and optimization of a construction scheme are realized. Disclosure of Invention The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the application provides the vacuum preloading construction decision method and system based on the knowledge graph and the electronic equipment, which can improve the accuracy and scientificity of vacuum preloading construction parameter setting. In a first aspect, an embodiment of the application provides a vacuum preloading construction decision method based on a knowledge graph. The vacuum preloading construction decision-making method based on the knowledge graph comprises the steps of constructing the knowledge graph of vacuum preloading construction, wherein the knowledge graph comprises construction element entities extracted from historical engineering data, semantic relations among the construction element entities and reasoning rules obtained based on association rule mining, obtaining an environment parameter data set and design indexes of a target area, carrying out reasoning matching by using the knowledge graph to obtain initial construction scheme parameters, constructing a finite element model based on the initial construction scheme parameters, carrying out numerical simulation, correcting the initial construction scheme parameters according to simulation results to obtain target construction scheme parameters, and generating control instructions aimi