A method and system for rapid detection and assessment of bearing capacity of post-disaster highway tunnels based on knowledge graph
By establishing a knowledge base in the knowledge graph field and chain rule reasoning for post-disaster highway tunnels, a rapid detection and evaluation method was constructed, which solved the problem of identifying the load capacity of the post-disaster tunnel, and achieved rapid and accurate quantities of lining disease identification and early warning value evaluation, avoiding operation The accident occurred during the process.
Patent Information
- Application Number
- CN202311473596.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-07
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2043-11-07
AI Technical Summary
The deformation characteristics and structural parameters of post-disaster highway tunnels in the prior art lack clear relevant parameters and a complete evaluation model, resulting in the failure to effectively identify and evaluate the load capacity of post-disaster highway tunnels, increasing the risk of accidents during operation.
Using a knowledge graph-based method, a knowledge base in the knowledge graph field of post-disaster highway tunnels is established, forward inference is carried out through chain rules to obtain the deformation data of the inner surface of the structure and the decay value of the local elastic modulus, and reverse inference is used to build a structural bearing capacity characterization system. And verify the prediction results through model experiments, and build a rapid detection and evaluation method and early warning value evaluation system.
It realizes rapid and accurate quantities perceived assessment, accurately identify lining diseases, avoids accidents during the operation of highway tunnels after the disaster, saves labor and time costs, and provides an assessment of the health status of the tunnel after the disaster.
Smart Images

Figure CN117745115B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of post-disaster highway tunnel structure safety, and in particular relates to a method and system for rapid detection and assessment of the bearing capacity of a post-disaster highway tunnel based on a knowledge graph. Background Art
[0002] Tunnel engineering is a control project on highways. Its overall structural performance and safety status during service have a significant impact on the smooth operation of highway traffic. Therefore, it is very important to accurately and quickly identify lining defects and obtain their relevant parameters to maintain tunnel operation and study the quantitative assessment technology of tunnel post-disaster structural damage.
[0003] However, for a long time, there has been no clear correlation parameter or prediction result for the deformation characteristics and structural parameters of post-disaster tunnels, and there is also a lack of a complete and systematic evaluation model. This has led to a lack of clear disease understanding and data support for the bearing capacity of post-disaster highway tunnels.
[0004] In summary, the lack of existing data and applications includes: deformation data characteristics and elastic modulus change function of post-disaster highway tunnels. There is no combination of big data knowledge graph to make corresponding deformation and structure predictions. There is a lack of knowledge graph domain knowledge base for post-disaster highway tunnels or the knowledge graph has not been applied to the assessment of post-disaster highway tunnels.
[0005] In order to solve the above-mentioned field combination problem, the present invention proposes a method for rapid detection and evaluation of the bearing capacity of post-disaster highway tunnels based on knowledge graphs. Big data is used to establish a knowledge graph domain knowledge base for post-disaster highway tunnels, and chain rules are extracted on the knowledge graph. The chain rules are forward-reasoned to obtain deformation data predictions of the rule body variables of the post-disaster highway tunnel and the post-disaster local elastic modulus function. Reverse reasoning is performed based on the prediction results to construct a characterization index system for the bearing capacity of the post-disaster highway tunnel structure. The correctness of the deformation data prediction and the post-disaster local elastic modulus value under the knowledge graph is verified by combining model tests, thereby constructing a knowledge graph and a method for rapid detection and evaluation of the post-disaster tunnel lining structure. As a rapid, accurate and quantitative perception assessment and a warning value evaluation system for post-disaster highway tunnel structures are provided. Summary of the invention
[0006] The present invention aims to overcome at least one defect (shortcoming) of the above-mentioned prior art and provide a method for rapid detection and assessment of the bearing capacity of a post-disaster highway tunnel based on a knowledge graph, so as to solve the problem in the prior art that after a disaster occurs in a highway tunnel, there is no clear understanding of the disease and data support for the bearing capacity of the highway tunnel, which leads to accidents during the operation of the post-disaster highway tunnel.
[0007] The technical solution adopted by the present invention is a method for rapid detection and assessment of post-disaster highway tunnels based on knowledge graph, which mainly includes the following steps:
[0008] S101: Establish and store knowledge base content management data in the knowledge graph of post-disaster highway tunnels;
[0009] S102: Based on the chain rule and forward reasoning, the deformation data of the inner surface of the structure and the attenuation value of the local elastic modulus after the disaster are obtained through the knowledge graph database;
[0010] S103: Based on the prediction results obtained by the chain rule, reverse reasoning is performed to construct a characterization system for the bearing capacity of the post-disaster highway tunnel structure lining;
[0011] S104: Verify deformation data prediction and post-disaster local elastic modulus function based on knowledge graph based on model test;
[0012] S105: Construct a knowledge graph and a method for rapid detection and assessment of the bearing capacity of post-disaster tunnel lining structures.
[0013] This method can be used as a fast, accurate and quantitative perception assessment, and provides an early warning value evaluation system for post-disaster highway tunnel structures, accurately and quickly identifying lining defects and avoiding accidents during post-disaster highway tunnel operations.
[0014] Preferably, in step S101, specifically, unstructured text language is extracted into structured data, established and stored in a knowledge base, and a knowledge graph domain knowledge base of post-disaster highway tunnels is established using big data to provide data support for subsequent reasoning.
[0015] Further preferably, in step S101, it also includes constructing a knowledge graph: extracting text knowledge elements of post-disaster highway tunnels based on hierarchical themes, extracting post-disaster highway tunnel features based on domain knowledge and machine learning, and then constructing a knowledge graph of post-disaster highway tunnels based on multi-feature association. The text knowledge element extraction includes: extracting and studying post-disaster highway tunnel knowledge elements based on analyzing the post-disaster highway tunnel lining data structure and thematic hierarchy, and obtaining the geological type of the post-disaster highway tunnel in combination with actual application needs, and extracting geological text knowledge elements.
[0016] Obtaining textual knowledge elements such as the tunnel's address type, disaster cause, and lining type can improve the construction of the post-disaster highway tunnel knowledge graph and make the evaluation indicators of the warning value more complete.
[0017] Further preferably, in step S102, the chain rule is an AMIE chain rule, and constructing the AMIE chain rule and performing forward reasoning specifically includes the following steps:
[0018] S21: establishing a rule head and a rule body of the post-disaster highway tunnel of the chain rule;
[0019] S22: Use the rule head to predict the regular body variables of the post-disaster highway tunnel lining to obtain the first prediction vector in the prediction result, and use the rule body to predict the regular body variables of the post-disaster highway tunnel lining to obtain the second prediction vector in the prediction result, and finally obtain the structural inner surface deformation data prediction results of the post-disaster highway tunnel regular body variables and the post-disaster local elastic modulus attenuation value.
[0020] More preferably, in step S22, it also includes reducing the elastic modulus of the material based on the degree of loss of the tunnel lining structure after the disaster, and the formula is:
[0021] in is the reduced elastic modulus, is the post-disaster reduction factor, is the elastic modulus of concrete, is the elastic modulus of the reinforced concrete lining structure.
[0022] Based on the reduction of the elastic modulus of the material obtained above, the condition of the highway tunnel after the disaster can be effectively seen, providing data support for judging the health status of the tunnel after the disaster.
[0023] Preferably, in step S103, the highway tunnel structure lining bearing capacity characterization system also includes the functional relationship between the structure inner surface deformation data and the post-disaster local elastic modulus, that is, the normal and post-disaster moduli and the lining arc angle Relationship Function, specifically:
[0024] First, the deformation data predicted by the AMIE chain rule in step S102 is combined with the elastic foundation beam and curved beam mechanics theory to connect the soil and the post-disaster highway tunnel lining structure. Then, the relevant system of the internal force characteristics of the structure is inversely calculated through the known deformation data. Finally, based on the degree of damage, the continuous deformation characteristics of the structure are obtained by coupling the normal and post-disaster moduli.
[0025] Preferably, in step S103, it also includes constructing a characterization index function relationship based on the inner surface deformation data of the post-disaster highway tunnel structure, specifically, the radial displacement, circumferential displacement, and actual displacement of the arc and the lining arc angle, respectively. The functional relationship between , , .
[0026] Preferably, the related system of the internal force characteristics specifically includes:
[0027] The lining is considered as an arc-shaped compression-bending structure. The radial displacement equation is established by combining the circular arc structure annular microelement physical equation, geometric equation and equilibrium equation. Differential equilibrium equations are used to obtain differential expressions of circumferential displacement and radial displacement. Combined with mechanical characteristics, analytical solutions of stress, shear force, axial force and bending moment under load are expressed by displacement, including:
[0028] The radial and circumferential force balance equations of the arc element are:
[0029] ,
[0030] ,
[0031] Displacement and mechanical characteristics:
[0032] ,
[0033] ,
[0034] ,
[0035] ,
[0036] Based on the predicted deformation characteristics and elastic modulus material characteristics, the internal force characteristics of the results are calculated, including the bending moment, shear force, axial force, and stress of the entire section. According to the current design specifications and calculation formulas, a rapid, accurate, quantitative perception assessment and an early warning value evaluation system for post-disaster highway tunnel structures are established.
[0037] Preferably, in step S104, it also includes taking the multi-section arc structure of the highway tunnel as the prototype, using 3D printing technology to produce a homogeneous arc model, and based on the indoor arc model test, providing a known disaster mode and measured deformation characteristics to verify the correctness of the chain rule deformation prediction and the rationality of the mechanical calculation of the structural bearing capacity.
[0038] Preferably, a system for rapid detection and assessment of the bearing capacity of post-disaster highway tunnels based on knowledge graphs specifically includes using a communication device to call a communication bus and a communication interface to transmit data, importing relevant parameters and keywords into an input device, and then using a knowledge graph database processor to call logic instructions in a storage device to process the data, and after the processing is completed, the result is exported through an output device, and the result is stored in a storage device. The present invention provides a simple-to-operate system, by inputting data such as the geological type, disaster cause, and lining type of the post-disaster highway tunnel to be detected into the system, the detection and assessment results of the post-disaster bearing capacity of the highway tunnel can be obtained quickly, and the health status of the post-disaster highway tunnel can be quickly evaluated, labor and time costs can be saved, and accidents during the operation of the post-disaster highway tunnel can be avoided.
[0039] Compared with the prior art, the present invention has the following advantages and technical achievements:
[0040] The present invention can quickly and accurately quantitatively perceive and evaluate the mechanical distribution of post-disaster highway tunnel linings based on the database tunnel deformation data and structural characteristics of the knowledge graph, and provide a warning value evaluation system for post-disaster highway tunnel structures. According to the study of the overall mechanical characteristic system of post-disaster highway tunnels, based on the knowledge graph, the deformation characteristics and material characteristics of the post-disaster tunnel lining structure are quickly obtained, and the post-disaster tunnel is analyzed as a whole based on the mechanical state, which is of great significance for the rapid and accurate preliminary evaluation of the post-disaster lining structure, and solves the problem of accidents occurring during the operation of post-disaster highway tunnels. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Figure 1 This is a flow chart of the method for rapid detection and assessment of the bearing capacity of post-disaster highway tunnels based on knowledge graphs of the present invention.
[0042] Figure 2 This is a text content storage structure diagram of the method for rapid detection and assessment of the bearing capacity of post-disaster highway tunnels based on the knowledge graph and based on the chain rule and forward reasoning of the present invention.
[0043] Figure 3 The present invention performs reverse reasoning based on the prediction results described in the chain rule, and provides a knowledge graph data storage structure diagram for a method for rapid detection and evaluation of the bearing capacity of post-disaster highway tunnels based on a knowledge graph.
[0044] Figure 4 This is a model test diagram of the knowledge graph-based rapid detection and assessment method for the bearing capacity of post-disaster highway tunnels based on model test verification of the present invention.
[0045] Figure 5 This is a structural diagram of an embodiment of the method for rapid detection and assessment of the bearing capacity of post-disaster highway tunnels based on knowledge graphs of the present invention.
[0046] Figure 6 It is a schematic diagram of modulus attenuation after a disaster in the present invention. DETAILED DESCRIPTION
[0047] The drawings of the present invention are only for illustrative purposes and should not be construed as limiting the present invention. In order to better illustrate the following embodiments, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product; it is understandable to those skilled in the art that some well-known structures and their descriptions in the drawings may be omitted.
[0048] like Figure 1 As shown, the knowledge graph provided by the present invention provides a method for rapid detection and assessment of the bearing capacity of a highway tunnel after a disaster, including:
[0049] Step S101, storing the knowledge graph domain knowledge base content management data of the post-disaster highway tunnel, extracting the unstructured text language into structured data, establishing and storing it in the knowledge base;
[0050] Step S102, establish a chain rule and forward reasoning, and cooperate with the knowledge base to obtain the surface data of the post-disaster tunnel structure and the local elastic modulus attenuation value; Step S103, based on the data results obtained by the chain rule, reverse reasoning is performed to obtain the post-disaster tunnel structure lining bearing capacity characterization system;
[0051] Step S104, verifying the deformation data and the post-disaster local elastic modulus attenuation function predicted by the knowledge graph based on the model test;
[0052] Step S105, construct a rapid assessment method for post-disaster highway tunnel lining structure based on the knowledge graph according to the results.
[0053] The method provided by the present invention can be used as a fast, accurate and quantitative perception assessment, and provides an early warning value evaluation system for post-disaster highway tunnel structures, which can accurately and quickly identify lining defects and avoid accidents during the operation of post-disaster highway tunnels.
[0054] Preferably, in step S101, Figure 2As shown in the figure, firstly, the knowledge graph domain knowledge base retrieval function is constructed, and the full-text retrieval technology of ElasticSearch is used. Based on the geological type, disaster cause, lining type and other factors, the knowledge element of the post-disaster highway tunnel lining is extracted and studied on the basis of analyzing the data structure and subject level of the post-disaster highway tunnel lining. In addition, the geological type of the post-disaster highway tunnel is obtained in combination with the actual application needs, and the geological text knowledge element is extracted. The dynamic weight ratio conditions of different parameters are configured for query, and the data is processed with weights of 2:5:3 respectively; the unstructured text language is extracted into structured data, and the knowledge graph domain knowledge base knowledge construction data is stored. After the data is structured, the natural language extraction is performed through the extraction model and semantic rules to intelligently extract and annotate the results, identify the knowledge graph construction information and store it in ElasticSearch and ArangoDB; the knowledge graph domain knowledge base map is used for intelligent analysis, and the knowledge model is used for intelligent analysis of the document library. After the model is trained, a stable model library is generated. Finally, the lining deformation database of the highway tunnel after the disaster is obtained under different weights, and the knowledge graph domain knowledge base map construction function is built.
[0055] Further preferably, in step S102, the chain rule is an AMIE chain rule, and constructing the AMIE chain rule and performing forward reasoning specifically includes the following steps:
[0056] S21: establishing a rule head and a rule body of the post-disaster highway tunnel of the chain rule;
[0057] S22: Use the rule head to predict the regular body variables of the post-disaster highway tunnel lining to obtain the first prediction vector in the prediction result, and use the rule body to predict the regular body variables of the post-disaster highway tunnel lining to obtain the second prediction vector in the prediction result, and finally obtain the structural inner surface deformation data prediction results of the post-disaster highway tunnel regular body variables and the post-disaster local elastic modulus attenuation value.
[0058] S21 specifically includes: first, adding a hanging edge, one end of which is a variable that has not appeared, and the other end is a variable that has appeared in the rule; then adding an instance edge, that is, an entity in the knowledge base; and finally, adding a closed edge connecting two elements that exist in the rule.
[0059] More preferably, if Figure 6 As shown, in step S22, it also includes reducing the material elastic modulus based on the degree of loss of the tunnel lining structure after the disaster, and the formula is:
[0060] in is the reduced elastic modulus, is the post-disaster reduction factor, is the elastic modulus of concrete, is the elastic modulus of the reinforced concrete lining structure.
[0061] Preferably, in step S103, the highway tunnel structure lining bearing capacity characterization system also includes the functional relationship between the structure inner surface deformation data and the post-disaster local elastic modulus, that is, the normal and post-disaster moduli and the lining arc angle Relationship Function, specifically:
[0062] First, the deformation data predicted by the AMIE chain rule in step S102 is combined with the elastic foundation beam and curved beam mechanics theory to connect the soil and the post-disaster highway tunnel lining structure. Then, the relevant system of the internal force characteristics of the structure is inversely calculated through the known deformation data. Finally, based on the degree of damage, the continuous deformation characteristics of the structure are obtained by coupling the normal and post-disaster moduli.
[0063] Preferably, in step S103, it also includes constructing a characterization index function relationship based on the inner surface deformation data of the post-disaster highway tunnel structure, specifically, the radial displacement, circumferential displacement, and actual displacement of the arc and the lining arc angle, respectively. The functional relationship between , , .
[0064] Preferably, the related system of the internal force characteristics specifically includes:
[0065] The lining is considered as an arc-shaped compression-bending structure. The radial displacement equation is established by combining the circular arc structure annular microelement physical equation, geometric equation and equilibrium equation. Differential equilibrium equations are used to obtain differential expressions of circumferential displacement and radial displacement. Combined with mechanical characteristics, analytical solutions of stress, shear force, axial force and bending moment under load are expressed by displacement, including:
[0066] The radial and circumferential force balance equations of the arc element are:
[0067] ,
[0068] ,
[0069] Displacement and mechanical characteristics:
[0070] ,
[0071] ,
[0072] ,
[0073] ,
[0074] Based on the predicted deformation characteristics and material characteristics of the elastic modulus, the internal force characteristics of the result are calculated, including the bending moment, shear force, axial force, and stress of the entire section. Figure 3 As shown, the knowledge base content management data of the knowledge graph of post-disaster highway tunnels is analyzed, auxiliary prediction is carried out based on related cases of the same type, the mechanical characteristics of the on-site post-disaster highway tunnel are analyzed based on the deformation characteristics, and relevant functions are constructed. According to the current design specifications and calculation formulas, a fast, accurate and quantitative perception assessment is established and an early warning value evaluation system for post-disaster highway tunnel structures is provided to conduct long-term process predictions.
[0075] Preferably, if Figure 4 As shown, in step S104, it also includes using the multi-segment arc structure of the highway tunnel as a prototype, using 3D printing technology to make a homogeneous arc model, and based on the indoor arc model test, given the known disaster mode and measured deformation characteristics, to verify the correctness of the chain rule deformation prediction and the rationality of the mechanical calculation of the structural bearing capacity. In order to clarify the accuracy of the training model, a model test is added to verify the arc geometric deformation and mechanical properties of the predicted model and the measured model. Based on this as a criterion, a knowledge graph and a post-disaster tunnel lining structure rapid detection and evaluation method are constructed as a rapid, accurate and quantitative perception evaluation and a post-disaster highway tunnel structure early warning value evaluation system.
[0076] Preferably, if Figure 5 As shown, a system for rapid detection and assessment of the bearing capacity of a post-disaster highway tunnel based on a knowledge graph specifically includes: using a communication device 308 to call a communication bus 303 and a communication interface 304 to transmit data, importing relevant parameters and keywords into an input device 305, and then calling the logical instructions in a storage 302 through a knowledge graph database processor 301 to process the data, and after the processing is completed, the result is exported through an output device 306, and the result is stored in a storage device 307. The present invention provides a simple-to-operate system, by inputting data such as the geological type, disaster cause, and lining type of the post-disaster highway tunnel to be detected into the system, the detection and assessment results of the post-disaster bearing capacity of the highway tunnel can be obtained quickly, so that the health status of the post-disaster highway tunnel can be quickly evaluated, labor and time costs are saved, and accidents during the operation of the post-disaster highway tunnel are avoided.
[0077] Specifically: In a post-disaster highway tunnel, under normal use, the lining elastic modulus E2=30GPa, Poisson's ratio is 0.2, the cross section is a rectangular cross section with a thickness of 0.3m and a width of 1m, the inner diameter r=5.4m, and the outer diameter R=6m. Based on the knowledge graph database of post-disaster highway tunnels, the keywords fire factor, 2 damages, and the surrounding geology are soft rock formations. It can be predicted that under this condition, the elastic modulus E1 of the affected area becomes 20GPa. Combined with the site, the deformation of the affected area is predicted through the knowledge graph, including the radial displacement and circumferential displacement of the arc. The affected section and the normal use section are calculated separately, the basic characteristics of the combined curved rod microelement are combined, and the physical equations, geometric equations and force balance equations are combined to inversely calculate the mechanical properties of each location through deformation, and the soil boundary conditions are combined to solve the functional relationship, so as to establish a knowledge graph and a warning value for rapid detection and evaluation of post-disaster tunnel lining structures.
[0078] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the technical solution of the present invention, and are not intended to limit the specific implementation methods of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the claims of the present invention shall be included in the protection scope of the claims of the present invention.
Claims
1. A method for rapid detection and assessment of the bearing capacity of a post-disaster highway tunnel based on a knowledge graph, comprising the following steps: S101: Establish and store knowledge base content management data in the knowledge graph of post-disaster highway tunnels; S102: Based on the chain rule and forward reasoning, the deformation data of the inner surface of the structure and the attenuation value of the local elastic modulus after the disaster are obtained through the knowledge graph database; The chain rule is the AMIE chain rule. Constructing the AMIE chain rule and performing forward reasoning specifically includes the following steps: S21: establishing a rule head and a rule body of the post-disaster highway tunnel of the chain rule; S22: predicting the regular body variables of the post-disaster highway tunnel lining using the rule head to obtain a first prediction vector in the prediction result, and predicting the regular body variables of the post-disaster highway tunnel lining using the rule body to obtain a second prediction vector in the prediction result, and finally obtaining the prediction result of the structural inner surface deformation data of the post-disaster highway tunnel regular body variables and the post-disaster local elastic modulus attenuation value; In step S22, it also includes reducing the material elastic modulus based on the degree of loss of the tunnel lining structure after the disaster, and the formula is: in is the reduced elastic modulus, is the post-disaster reduction factor, is the elastic modulus of concrete, is the elastic modulus of the reinforced concrete lining structure; S103: Construct a characterization system for the bearing capacity of post-disaster highway tunnel structure linings through reverse reasoning based on prediction results; In step S103, the highway tunnel structure lining bearing capacity characterization system includes the functional relationship between the structure inner surface deformation data and the post-disaster local elastic modulus, that is, the normal and post-disaster moduli and the lining arc angle Relationship Function, specifically: First, the deformation data predicted by the AMIE chain rule in step S102 is combined with the elastic foundation beam and curved beam mechanics theory to connect the soil and the post-disaster highway tunnel lining structure. Then, the relevant system of the internal force characteristics of the structure is inversely calculated through the known deformation data. Finally, the continuous deformation characteristics of the structure are obtained by coupling the normal and post-disaster moduli based on the degree of damage. In step S103, it also includes constructing a characterization index function relationship based on the deformation data of the inner surface of the highway tunnel structure after the disaster, specifically, the radial displacement, circumferential displacement, and actual displacement of the arc and the lining arc angle The functional relationship between , , ; The relevant system of the internal force characteristics specifically includes: The lining is considered as an arc-shaped compression-bending structure. The radial displacement equation is established by combining the circular arc structure annular microelement physical equation, geometric equation and equilibrium equation. v Differential equilibrium equations are used to obtain differential expressions of circumferential displacement and radial displacement. Combined with mechanical characteristics, analytical solutions of stress, shear force, axial force and bending moment under load are expressed by displacement, including: The radial and circumferential force balance equations of the arc element are: , , Displacement and mechanical characteristics: , , , , Based on the predicted deformation characteristics and material characteristics of elastic modulus, the internal force characteristics of the results are calculated, including bending moment, shear force, axial force, and stress of the entire section; S104: Verify the prediction results of deformation data under the knowledge graph and the local elastic modulus function after the disaster based on model tests; S105: Construct a knowledge graph and a method for rapid detection and assessment of the bearing capacity of post-disaster tunnel lining structures.
2. According to the knowledge graph-based rapid detection and assessment method for post-disaster highway tunnel bearing capacity according to claim 1, it is characterized in that: In step S101 , specifically, unstructured text language is extracted into structured data, which is established and stored in a knowledge base.
3. The method for rapid detection and assessment of the bearing capacity of post-disaster highway tunnels based on knowledge graph according to claim 2 is characterized in that: In step S102, it also includes establishing a knowledge graph: extracting text knowledge elements of post-disaster highway tunnels based on hierarchical themes, extracting features of post-disaster highway tunnels based on domain knowledge and machine learning, and then constructing a knowledge graph of post-disaster highway tunnels based on multi-feature association; wherein the text knowledge element extraction includes: extracting and studying post-disaster highway tunnel knowledge elements based on analyzing the data structure and thematic hierarchy of post-disaster highway tunnel linings, and obtaining the geological type of post-disaster highway tunnels in combination with actual application needs, and extracting geological text knowledge elements.
4. The method for rapid detection and assessment of the bearing capacity of post-disaster highway tunnels based on knowledge graph according to claim 3 is characterized in that: In step S104, it also includes using 3D printing technology to produce a homogeneous arc model based on the multi-section arc structure of the highway tunnel as a prototype, and based on the indoor arc model test, given the known disaster mode and measured deformation characteristics, to verify the correctness of the chain rule deformation prediction and the rationality of the mechanical calculation of the structural bearing capacity.
5. A system for rapid detection and assessment of the bearing capacity of a post-disaster highway tunnel based on a knowledge graph according to the method for rapid detection and assessment of the bearing capacity of a post-disaster highway tunnel based on a knowledge graph according to any one of claims 1 to 4, characterized in that: Use the communication device to call the communication bus and communication interface to transmit data, import relevant parameters and keywords into the input device, and then use the knowledge graph database processor to call the logical instructions in the memory to process the data. After the processing is completed, the results are exported through the output device and the structure is stored in the storage device.
