Digital twin-driven TBM tunnel construction surrounding rock collapse risk dynamic assessment method and device and storage medium

Abstract

The invention relates to the technical field of geospatial information systems, and particularly discloses a digital twin-driven TBM tunnel construction surrounding rock collapse risk dynamic assessment method and device and a storage medium, the method comprises the steps of constructing a TBM tunnel construction surrounding rock collapse knowledge graph mode layer, the primary concept comprising a disaster-bearing body, disaster-inducing factors and a disaster-pregnant environment; under the constraint of the mode layer, advanced geological forecast data, TBM operation equipment parameter data and historical collapse event record data are utilized to construct a knowledge graph data layer; building a TBM tunnel construction surrounding rock collapse risk assessment model under the guidance of the knowledge graph, and continuously optimizing the model; and finally, carrying out instant risk assessment by using the trained risk assessment model. According to the method, the knowledge graph is utilized to guide the deep learning model, all surrounding rock collapse risk factors are comprehensively and deeply analyzed and evaluated, and efficient, accurate and timely TBM tunnel construction surrounding rock collapse risk dynamic evaluation is helped to be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of geospatial information systems, and in particular to a digital twin-driven method, device, and storage medium for dynamic assessment of surrounding rock collapse risk in TBM tunnel construction. Background Art

[0002] Tunnel boring machines (TBMs) have been widely used in the construction of ultra-long, deep tunnels due to their high construction speed, high quality, minimal disturbance to the surrounding rock, and environmental friendliness. However, TBMs have poor geological adaptability when faced with complex geological conditions, such as soft rock, fault fracture zones, aquifers, and karst caves. This can easily lead to hazards such as rock collapse, which can cause cutterhead jamming, equipment damage, extended construction schedules, and even casualties. Therefore, comprehensive assessment of rock collapse risks during TBM tunnel construction is crucial. By providing timely and accurate feedback on risk indicators, TBMs can provide critical guidance for tunnel construction, thereby mitigating the impact of rock collapse risks on railway construction safety and minimizing losses in manpower and resources.

[0003] Currently, the prediction of surrounding rock collapse risk primarily relies on advanced geological prediction technology, which analyzes forecast data based on expert experience. This technology lacks immediacy, is complex and time-consuming, and makes dynamic assessment difficult. Furthermore, in TBM tunnels, conventional multi-source advanced geological prediction technology has certain limitations in implementation due to economic constraints, construction schedules, and installation space constraints, making it impossible to fully and accurately obtain data on the geological conditions ahead of the tunnel. Modern TBMs are equipped with a large number of sensors to monitor equipment status in real time, collecting massive amounts of equipment operating parameter data at an extremely high frequency. These raw and characteristic parameters fully reflect the interaction between rock and machine. When combined with various machine learning algorithms, they can, to a certain extent, reflect the geological conditions of the tunnel surrounding rock and achieve prediction of surrounding rock collapse risk. However, the accuracy of this method is highly dependent on the precision of the raw data.

[0004] Therefore, it is urgent to propose an accurate, timely and efficient dynamic assessment method for surrounding rock collapse risk during TBM tunnel construction. Summary of the Invention

[0005] In order to address the many limitations and shortcomings of existing technical methods in assessing surrounding rock collapse during TBM tunnel construction, such as poor immediacy, complicated procedures, time-consuming and low reliability, and the limited, fragmented, complex and highly unstructured data characteristics of multi-source advanced geological prediction data, as well as the fact that modern TBM equipment can provide massive parameter data reflecting rock-machine interaction, the present invention provides a digital twin-driven dynamic assessment method, equipment and storage medium for surrounding rock collapse risk assessment during TBM tunnel construction, which couples and analyzes limited advanced geological prediction data with massive TBM equipment operating parameter data. This method uses knowledge graphs to effectively integrate professional knowledge and expert experience in the field of geological engineering under surrounding rock collapse risks, constructs a structured TBM tunnel construction collapse risk knowledge representation, establishes connections between knowledge, forms a TBM tunnel construction surrounding rock collapse risk knowledge graph, explores the potential correlation and regularity between surrounding rock collapse disaster factors, systematically records and manages the relationship between various factors, and uses this knowledge graph to guide deep learning models to comprehensively and deeply analyze and evaluate various surrounding rock collapse risk factors, helping to achieve efficient, accurate and timely dynamic assessment of surrounding rock collapse risks in TBM tunnel construction, solving the problems mentioned in the above background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a digital twin-driven dynamic assessment method for surrounding rock collapse risk in TBM tunnel construction, comprising the following steps:

[0007] S101. Construct a knowledge graph model layer for surrounding rock collapse risk during TBM tunnel construction.

[0008] S102. Define surrounding rock collapse risk indicators and integrate multi-source data to establish a knowledge graph data layer for surrounding rock collapse risk in TBM tunnel construction;

[0009] S103. Establishment and iterative optimization of a dynamic assessment model for surrounding rock collapse risk guided by knowledge graph;

[0010] S104. Dynamic assessment and early warning.

[0011] Preferably, the knowledge graph model layer of the TBM tunnel construction surrounding rock collapse risk in step S101 specifically includes: taking into account the key features of multi-feature association, geological scene context, and geological entity constraints in the field of surrounding rock collapse, using ontology technology to design the model layer, and realizing the standardized description and formal expression of the TBM tunnel construction surrounding rock collapse risk knowledge concept system and its attributes, relationships and rules, to form the TBM tunnel construction surrounding rock collapse risk knowledge graph model layer.

[0012] Preferably, in step S101, ontology technology is used to design a model layer, and the knowledge graph ontology of surrounding rock collapse risk in TBM tunnel construction is divided into three first-level concepts: hazard-bearing body, hazard-causing factors, and disaster-pregnant environment. The hazard-bearing body specifically includes tunnel type, tunnel location, support structure, and structural integrity; the hazard-causing factors include geological structure, construction method, external load, and construction error; and the disaster-pregnant environment includes groundwater level, geological structure, seismic activity, and historical disaster records.

[0013] The knowledge graph model layer for surrounding rock collapse risk during TBM tunnel construction includes concept set construction and relationship expression, specifically including the following: concept modeling of hazard-bearing bodies, concept modeling of hazard-causing factors, concept modeling of hazard-prone environments, and multi-relationship description;

[0014] Conceptual modeling of the hazard-bearing body: In the case of rock collapse during TBM tunnel construction, the hazard-bearing body mainly refers to the tunnel structure or area that may be affected by the rock collapse.

[0015] Conceptual modeling of hazard factors: In surrounding rock collapse during TBM tunnel construction, hazard factors mainly refer to factors that may cause surrounding rock collapse;

[0016] Concept modeling of disaster-prone environment: In the surrounding rock collapse during TBM tunnel construction, the disaster-prone environment mainly refers to the environmental factors that provide conditions for collapse events during TBM tunnel construction.

[0017] The multi-relationship description includes the following: ① Conceptual relationships: Conceptual relationships are reflected in the semantic connections between the three major concepts of hazard-bearing objects, hazard-causing factors, and hazard-prone environments, as well as between their sub-concepts. These relationships include belonging, co-location, and hierarchical relationships, and are constructed based on a domain ontology tree. This ontology tree is used to express the hierarchical and semantic connections between these concepts and their sub-concepts when considering the risk of surrounding rock collapse during TBM tunnel construction, allowing for a systematic description and analysis of how different concepts interact, influence, and depend on each other. ② Spatial relationships: Spatial relationships describe the relative position and relationships between objects in space. ③ Attribute relationships: Attribute relationships describe the characteristics or attributes of factors involved in tunnel construction and their interrelationships. Qualitative relationships, such as the properties of weak rock mass, require only the determination of the type of relationship that exists. Quantitative relationships involve the comparison of specific numerical values, such as the amount of water produced in a water-rich environment. ④ Temporal relationships: Temporal relationships describe the temporal sequence, duration, or changes of events during tunnel construction.

[0018] Preferably, the definition of the surrounding rock collapse risk index and the multi-source data association and integration in step S102 are used to establish a knowledge graph data layer of surrounding rock collapse in TBM tunnel construction, specifically including: extracting the risk classification attributes and semantic features of surrounding rock collapse in TBM tunnel construction according to the definition of surrounding rock collapse risk index, and then collecting multi-source data, including advanced geological forecast data, TBM equipment operating parameter data and historical collapse data; matching and aligning the data from these different sources to ensure their consistency in time, space coordinates and categories, and forming comprehensive geological and risk information through data fusion technology; standardizing all data to establish a knowledge graph data layer of surrounding rock collapse risk in TBM tunnel construction.

[0019] Preferably, in step S102, the following steps are specifically included:

[0020] Step S1021: Define surrounding rock collapse risk indicators: Based on actual surrounding rock collapse risk management requirements, define and extract relevant risk indicators, including stability indicators such as lining strength, support system bearing capacity, and stratum deformation; geological indicators such as the physical and mechanical properties of soil and rock, and groundwater level changes; and construction status indicators such as TBM operating status, construction progress, and equipment health status, to provide clear standards and goals for data collection and analysis.

[0021] Step S1022: Collect multi-source data: Collect multi-source data related to the above-mentioned risk indicators, including advanced geological forecast data, TBM equipment operating parameter data, and records of collapse risk events in previous tunnel construction, to provide basic information for subsequent risk analysis and knowledge graph construction;

[0022] Step S1023, data matching and alignment: matching and aligning data from different sources to ensure consistency in time, spatial coordinates, and categories;

[0023] Step S1024, data fusion: using statistical analysis methods or machine learning model technology to fuse multi-source data and extract comprehensive geological and risk information;

[0024] Step S1025, data standardization processing: standardize all data to ensure consistency of data format and unit;

[0025] Step S1026, establishing a knowledge graph data layer: based on the processed data, establishing a knowledge graph data layer for surrounding rock collapse risks during TBM tunnel construction.

[0026] Preferably, the establishment and iterative optimization of the dynamic assessment model for surrounding rock collapse risk in TBM tunnel construction under the guidance of the knowledge graph in step S103 specifically include: designing the framework of the dynamic assessment model and determining the assessment method based on the concepts and relationships defined in the knowledge graph; training the model with historical data and real-time data, evaluating the accuracy and reliability of the model through cross-validation methods, and continuously adjusting and optimizing.

[0027] Preferably, step S103 specifically includes the following steps:

[0028] Step S1031, model framework design: based on the concepts and relationships defined in the knowledge graph, design the framework of the dynamic evaluation model;

[0029] Step S1032: Model training and validation: Use historical data and real-time data to train the model. Use cross-validation and other validation methods to evaluate the accuracy and reliability of the model to ensure that it can effectively predict landslide risks.

[0030] Step S1033: Feedback and Optimization: Collect feedback between the model prediction results and actual events, analyze the model's errors and deficiencies, optimize the model based on the feedback, adjust the algorithm and parameters, and improve prediction accuracy.

[0031] Preferably, the dynamic assessment and early warning in step S104 specifically includes: continuously acquiring geological information, TBM equipment excavation parameters, and operating status within the tunnel through real-time monitoring and data collection; processing the data and inputting it into a dynamic assessment model for immediate risk assessment; and automatically generating a landslide risk report based on the model's output, identifying potential risk areas and severity levels, and issuing early warnings. Early warning strategies can also be optimized based on feedback information to improve the system's accuracy and response speed, thereby achieving effective management and control of tunnel collapse risks.

[0032] On the other hand, to achieve the above-mentioned object, the present invention further provides the following technical solution: an electronic device, comprising: a processor; and a memory for storing one or more programs;

[0033] When the one or more programs are executed by the processor, the processor executes the digital twin-driven dynamic assessment method for surrounding rock collapse risk in TBM tunnel construction.

[0034] On the other hand, to achieve the above-mentioned purpose, the present invention also provides the following technical solution: a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the digital twin-driven dynamic assessment method for surrounding rock collapse risk in TBM tunnel construction.

[0035] The beneficial effects of the present invention are:

[0036] 1) The method of the present invention uses a knowledge graph to effectively integrate the professional knowledge and expert experience in the field of geological engineering on surrounding rock collapse risk, construct a structured knowledge representation of TBM tunnel construction collapse risk, establish connections between knowledge, and form a knowledge graph of surrounding rock collapse risk in TBM tunnel construction. This knowledge graph explores the potential correlations and regularities between surrounding rock collapse disaster factors, systematically records and manages the relationships between various factors, and uses this knowledge graph to guide a deep learning model to comprehensively and deeply analyze and evaluate various surrounding rock collapse risk factors, helping to achieve efficient, accurate, and timely dynamic assessment of surrounding rock collapse risk in TBM tunnel construction.

[0037] 2) The method of the present invention effectively combines professional geological knowledge and advanced machine learning technology to more accurately analyze and assess the risk of surrounding rock collapse during TBM tunnel construction. Because the knowledge graph provides it with rich prior knowledge, the model can better understand and process complex geological data. Constructing and maintaining a knowledge graph of collapse risks in TBM tunnel construction helps to organize and preserve professional knowledge in the field of tunnel engineering, and promotes knowledge sharing and inheritance. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a flowchart of the steps of the dynamic assessment method for surrounding rock collapse risk during TBM tunnel construction driven by digital twins;

[0039] Figure 2 This is a schematic diagram of the knowledge map of surrounding rock collapse risks during TBM tunnel construction;

[0040] Figure 3 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention;

[0041] In the figure, 210 is a processor; 220 is a memory. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0043] The present invention provides a technical solution: a digital twin driven TBM tunnel construction surrounding rock collapse risk dynamic assessment method, the process is as follows Figure 1As shown in the figure, a knowledge graph of surrounding rock collapse risk during TBM tunnel construction is first constructed. Based on the constructed knowledge graph, a dynamic assessment model for surrounding rock collapse risk during TBM tunnel construction is established to achieve risk prediction. Specifically, the following steps are taken: constructing a knowledge graph model layer for surrounding rock collapse risk during TBM tunnel construction; associating surrounding rock collapse risk indicator definitions and multi-source data to establish a knowledge graph data layer for surrounding rock collapse risk during TBM tunnel construction; using the knowledge graph to guide the establishment and iterative optimization of a dynamic assessment model for surrounding rock collapse risk during TBM tunnel construction; and dynamic assessment and early warning.

[0044] The implementation process of the present invention comprises the following steps:

[0045] Step 1: Construct a knowledge graph model layer for surrounding rock collapse risk in TBM tunnel construction.

[0046] By reviewing the research of experts in the field of surrounding rock collapse risk, using ontology technology to design a model layer, taking into account the key characteristics of multi-feature association, geological scenario context, and geological entity constraints in the field of tunnel collapse, a standardized description and formal expression of the knowledge concept system of surrounding rock collapse risk in TBM tunnel construction and its attributes, relationships and rules are achieved.

[0047] The ontology of the pattern layer is a collection of terms used to describe a field. It is a clear and detailed description of the concept system, which determines the objects, concepts, attributes and their mutual relationships in the field. Its organizational structure is usually classified and hierarchical, and is expressed and stored in a form suitable for use in computer systems. Constructing an ontology can provide constraints and specifications for the expression of instances in the knowledge graph. The knowledge graph instances formed under the framework of the ontology not only have a strong hierarchical structure and low redundancy, but are also easier to expand and supplement. This method divides the knowledge graph ontology of surrounding rock collapse risk of TBM tunnel construction into three major categories: hazard-bearing bodies, hazard-causing factors and hazard-prone environments, i.e., three first-level concepts. Starting from the top-level concepts, the concepts, attributes, relationships and rules are modeled for knowledge expression to form the conceptual model and logical basis of the knowledge graph of surrounding rock collapse risk of TBM tunnel construction. The constructed pattern layer of the knowledge graph of surrounding rock collapse risk of TBM tunnel construction is as follows: Figure 2 As shown, the details are as follows:

[0048] (1) Conceptual modeling of disaster-prone bodies

[0049] In the case of rock collapse during TBM tunnel construction, the hazard-bearing body mainly refers to the tunnel structure or area that may be affected by the collapse, including tunnel type, tunnel location, support structure, structural integrity, etc.

[0050] (2) Conceptual modeling of disaster factors

[0051] In the case of rock collapse during TBM tunnel construction, the hazard-causing factors mainly refer to the factors that may cause tunnel collapse, including geological structure (soil type, rock strength, groundwater level, etc.), construction methods, external loads, construction errors, etc.

[0052] (3) Conceptual modeling of disaster-prone environments

[0053] In the case of rock collapse during TBM tunnel construction, the disaster-pregnant environment mainly refers to the environmental factors that provide conditions for rock collapse during TBM tunnel construction, including geological structure (strata, faults, rock and soil properties, etc.), groundwater level, seismic activity, historical disaster records, etc.

[0054] (4) Description of multivariate relationships

[0055] ① Conceptual relationships: Conceptual relationships are reflected in the semantic connections between the three major concepts of hazard-bearing body, hazard-causing factors, and hazard-prone environment, as well as between their internal sub-concepts. These relationships include belonging (for example, a certain support structure belongs to the hazard-bearing body of the tunnel), co-location (for example, seismic activity and groundwater level are both components of the hazard-prone environment), and superior and subordinate (for example, soft soil layer is a specific instance of geological structure). These relationships are constructed based on a domain ontology tree. The ontology tree is used to express the hierarchical and semantic connections between these concepts and their sub-concepts when landslide risks occur during TBM tunnel construction, so as to systematically describe and analyze how different concepts interact, influence, and depend on each other;

[0056] ② Spatial relations: Spatial relations describe the relative positions and relationships between objects in space, including topological relations (e.g., the contact relationship between the support structure and the tunnel wall), metric relations (e.g., the distance between the groundwater level and the tunnel bottom), and directional relations (e.g., the position of the landslide area relative to the tunnel).

[0057] ③ Attribute relationships: Attribute relationships describe the characteristics or properties of various factors in tunnel construction and their interrelationships. Qualitative relationships, such as the properties of weak rock mass (hard, relatively hard, weak, extremely weak), only require determining the type of relationship that exists. Quantitative relationships include comparisons of specific values, such as the amount of water produced in a water-rich situation. Other relationships may involve a broader knowledge system, such as introducing external geological time knowledge to explain the sequential relationship of sedimentary rock layers;

[0058] ④ Temporal relationships: Temporal relationships describe the temporal sequence, duration, or evolution of events during tunnel construction. In the context of rock collapse risk during TBM tunnel construction, this involves the evolution of the geological environment, such as the impact of geological structures formed at different geological stages on tunnel construction. For example, older sedimentary rock layers are typically located at greater depths, while newer layers are located at shallower depths. This temporal sequence is crucial for understanding the geological conditions likely to be encountered during tunnel construction.

[0059] Step 2: Define surrounding rock collapse risk indicators and integrate multi-source data to establish a knowledge graph data layer for surrounding rock collapse risk in TBM tunnel construction.

[0060] The rock collapse risk index for TBM tunnel construction is derived from a comprehensive analysis of numerous case studies and empirical findings by experts in this field. It serves as a crucial basis for subsequent rock collapse risk analysis and assessment during TBM tunnel construction. Multi-source data, including advanced geological forecasts, TBM equipment operating parameters, and historical collapse data, provides the foundation for subsequent risk assessments. Knowledge graphs can effectively organize, express, correlate, integrate, and comprehensively utilize the rich semantic information contained in this knowledge data.

[0061] Step 2.1, Define Rockfall Risk Indicators: Based on actual rockfall risk management needs, define and extract relevant risk indicators to provide clear standards and targets for data collection and analysis. These indicators may include stability indicators such as lining strength, support system bearing capacity, and ground deformation; geological indicators such as the physical and mechanical properties of soil and rock, and groundwater level changes; and construction status indicators such as TBM operating status, construction progress, and equipment health.

[0062] Step 2.1: Collect multi-source data: This includes data related to the aforementioned risk indicators, including advanced geological forecast data (data obtained through geological radar scanning, drilling data, rock and soil sampling and analysis, etc.) to understand the geological conditions ahead of the tunnel; TBM operating equipment parameter data (data recording the real-time operating status of the TBM, such as thrust, tunneling speed, torque, penetration, vibration data, temperature data, etc.); and records of collapse incidents during previous tunnel construction and past risk assessment reports. This data will provide foundational information for subsequent risk analysis and knowledge graph construction.

[0063] Step 2.3, Data Matching and Alignment: Match and align data from different sources to ensure consistency in time, spatial coordinates, and categories. Temporal alignment unifies the timestamps across different datasets to facilitate comparison and analysis of data trends; spatial alignment ensures consistent spatial coordinates across all data; and category alignment unifies data categories to ensure consistency in type and format.

[0064] Step 2.4, Data Fusion: Using statistical analysis methods, machine learning models, or data mining techniques, advanced geological forecast data and TBM equipment operating parameter data are integrated to extract comprehensive geological and risk information.

[0065] Step 2.5, Data Standardization: Standardize all data to ensure consistency in data format and units. This includes: format conversion, converting data to a unified format; unit unification, converting and unifying units across different data sets;

[0066] Step 2.6, establish the knowledge graph data layer: Based on the processed data above, establish the knowledge graph data layer for surrounding rock collapse risk in TBM tunnel construction:

[0067] Step 3: Establish and iteratively optimize the dynamic assessment model for surrounding rock collapse risk during TBM tunnel construction guided by the knowledge graph;

[0068] The constructed knowledge graph for rock collapse risk associated with TBM tunnel construction defines various concepts (such as geological characteristics and equipment parameters) and their relationships (such as influence and correlation). Based on the established spatial, attribute, and temporal relationships, a dynamic assessment model for rock collapse risk associated with TBM tunnel construction was constructed. This model comprehensively considers geological factors, construction parameters, and environmental conditions during tunnel construction, using a data-driven approach to assess collapse risk in real time. The model is then iteratively optimized using feedback from actual construction data and risk events to improve its prediction accuracy and reliability.

[0069] Step 3.1. Model framework design: Based on the concepts and relationships defined in the knowledge graph, design the framework of the dynamic assessment model. This includes determining the model's input variables (such as geological characteristics and equipment parameters), output results (such as landslide risk level), and assessment methods (such as statistical analysis and machine learning algorithms).

[0070] Step 3.2: Model training and validation: Use historical and real-time data to train the model. Use cross-validation and other validation methods to evaluate the model's accuracy and reliability to ensure it can effectively predict landslide risk.

[0071] Step 3.3, Feedback and Optimization: Collect feedback between the model's predictions and actual events, analyze the model's errors and deficiencies, and optimize the model based on the feedback, adjusting the algorithm and parameters to improve prediction accuracy.

[0072] Step 4: Dynamic Assessment and Early Warning

[0073] The real-time monitoring and data acquisition system can continuously obtain geological information within the tunnel, the operating status of the TBM equipment, and other relevant data. This data is input into the dynamic assessment model for surrounding rock collapse risk during TBM tunnel construction to conduct an immediate risk assessment. Based on the output of the model, a collapse risk report is automatically generated to identify potential risk areas and their severity.

[0074] Regularly evaluate the effectiveness of the early warning system and optimize the early warning strategy based on feedback information to improve the accuracy and response speed of the system, thereby achieving effective management and control of tunnel collapse risks.

[0075] The digital twin-driven dynamic assessment method for surrounding rock collapse risk in TBM tunnel construction proposed in this invention effectively combines professional geological knowledge and advanced machine learning technology, and can more accurately analyze and evaluate the risk of surrounding rock collapse in TBM tunnel construction. Moreover, because the knowledge graph provides it with rich prior knowledge, the model can better understand and process complex geological data; constructing and maintaining the knowledge graph of collapse risk in TBM tunnel construction helps to organize and preserve professional knowledge in the field of tunnel engineering, and promotes knowledge sharing and inheritance.

[0076] Based on the same inventive concept as the above method embodiment, the embodiment of the present application further provides an electronic device, such as Figure 2 As shown, the device includes: a processor 210; and a memory 220 for storing one or more programs;

[0077] When the one or more programs are executed by the processor 210, the processor executes the digital twin-driven dynamic assessment method for surrounding rock collapse risk in TBM tunnel construction.

[0078] The digital twin-driven dynamic assessment method for surrounding rock collapse risk during TBM tunnel construction includes the following steps:

[0079] Construct a knowledge graph model layer for surrounding rock collapse risk during TBM tunnel construction;

[0080] Define surrounding rock collapse risk indicators and integrate multi-source data to establish a knowledge graph data layer for surrounding rock collapse risk in TBM tunnel construction;

[0081] Establishment and iterative optimization of a dynamic assessment model for surrounding rock collapse risk guided by knowledge graph;

[0082] Dynamic assessment and early warning.

[0083] Based on the same inventive concept as the above-mentioned method embodiment, the embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by the processor 210 to implement the digital twin-driven dynamic assessment method for surrounding rock collapse risk in TBM tunnel construction.

[0084] The digital twin-driven dynamic assessment method for surrounding rock collapse risk during TBM tunnel construction includes the following steps:

[0085] Construct a knowledge graph model layer for surrounding rock collapse risk during TBM tunnel construction;

[0086] Define surrounding rock collapse risk indicators and integrate multi-source data to establish a knowledge graph data layer for surrounding rock collapse risk in TBM tunnel construction;

[0087] Establishment and iterative optimization of a dynamic assessment model for surrounding rock collapse risk guided by knowledge graph;

[0088] Dynamic assessment and early warning.

[0089] In the several embodiments provided in the embodiments of the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or can be implemented using a combination of dedicated hardware and computer instructions.

[0090] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0091] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk. It should be noted that, in this article, the terms "include", "comprising" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such a process, method, article or device. Without further constraints, an element defined by the phrase "comprises a..." does not preclude the existence of additional identical elements in the process, method, article or apparatus that includes the element.

[0092] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "an", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0093] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0094] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0095] The references to "first" and "second" in the embodiments merely distinguish similar objects and do not represent a specific ordering of the objects. It is understood that the specific order or precedence of "first" and "second" can be interchanged where appropriate. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein.

[0096] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A digital twin-driven dynamic assessment method for surrounding rock collapse risk in TBM tunnel construction, characterized by: The steps include: S101. Construct a knowledge graph model layer for surrounding rock collapse risk during TBM tunnel construction. S102. Define surrounding rock collapse risk indicators and integrate multi-source data to establish a knowledge graph data layer for surrounding rock collapse risk in TBM tunnel construction; S103. Establishment and iterative optimization of a dynamic assessment model for surrounding rock collapse risk guided by knowledge graph; S104. Dynamic assessment and early warning.

2. The method for dynamic assessment of surrounding rock collapse risk during TBM tunnel construction driven by digital twins according to claim 1 is characterized by: The knowledge graph model layer of the TBM tunnel construction surrounding rock collapse risk in step S101 specifically includes: taking into account the key features of multi-feature association, geological scene context, and geological entity constraints in the field of surrounding rock collapse, using ontology technology to design the model layer, and realizing the standardized description and formal expression of the TBM tunnel construction surrounding rock collapse risk knowledge concept system and its attributes, relationships and rules, thereby forming the TBM tunnel construction surrounding rock collapse risk knowledge graph model layer.

3. The method for dynamic assessment of surrounding rock collapse risk during TBM tunnel construction driven by digital twins according to claim 1 or 2, characterized in that: In step S101, the model layer is designed using ontology technology. The knowledge graph of surrounding rock collapse risk in TBM tunnel construction is divided into three first-level concepts: hazard-bearing body, hazard-causing factors, and disaster-pregnant environment. Hazard-bearing body specifically includes tunnel type, tunnel location, support structure, and structural integrity; hazard-causing factors include geological structure, construction method, external load, and construction error; and disaster-pregnant environment includes groundwater level, geological structure, seismic activity, and historical disaster records. The constructed knowledge graph model layer for surrounding rock collapse risk during TBM tunnel construction includes concept set construction and relationship expression, specifically including the concept modeling of hazard-bearing bodies, hazard-causing factors, and hazard-prone environments, as well as multi-relationship descriptions. The multi-relationship descriptions include: ① Conceptual relationships: Conceptual relationships are reflected in the semantic connections between the three major concepts of hazard-bearing bodies, hazard-causing factors, and hazard-prone environments, as well as between their internal sub-concepts; ② Spatial relationships: Spatial relationships describe the relative positions and relationships between objects in space; ③ Attribute relationships: Attribute relationships describe the characteristics or attributes of factors in tunnel construction and their mutual relationships; ④ Temporal relationships: Temporal relationships describe the temporal sequence, duration, or changes of events during tunnel construction.

4. The method for dynamic assessment of surrounding rock collapse risk during TBM tunnel construction driven by digital twins according to claim 1 is characterized by: The definition of surrounding rock collapse risk indicators and the association and integration of multi-source data in step S102 establish a knowledge graph data layer for surrounding rock collapse in TBM tunnel construction, specifically including: extracting the risk classification attributes and semantic features of surrounding rock collapse in TBM tunnel construction based on the definition of surrounding rock collapse risk indicators, and then collecting multi-source data, including advanced geological prediction data, TBM equipment operating parameter data, and historical collapse data; matching and aligning data from these different sources to ensure their consistency in time, spatial coordinates, and categories, and forming comprehensive geological and risk information through data fusion technology; and standardizing all data to establish a knowledge graph data layer for surrounding rock collapse risk in TBM tunnel construction.

5. The method for dynamic assessment of surrounding rock collapse risk during TBM tunnel construction driven by digital twins according to claim 1 or 4, characterized in that: In step S102, the following steps are specifically included: Step S1021: Define surrounding rock collapse risk indicators: Based on actual surrounding rock collapse risk management requirements, define and extract relevant risk indicators, including stability indicators such as lining strength, support system bearing capacity, and stratum deformation; geological indicators such as the physical and mechanical properties of soil and rock, and groundwater level changes; and construction status indicators such as TBM operating status, construction progress, and equipment health status, to provide clear standards and goals for data collection and analysis. Step S1022: Collect multi-source data: Collect multi-source data related to the above-mentioned risk indicators, including advanced geological forecast data, TBM equipment operating parameter data, and records of collapse risk events in previous tunnel construction, to provide basic information for subsequent risk analysis and knowledge graph construction; Step S1023, data matching and alignment: matching and aligning data from different sources to ensure consistency in time, spatial coordinates, and categories; Step S1024, data fusion: using statistical analysis methods or machine learning model technology to fuse multi-source data and extract comprehensive geological and risk information; Step S1025, data standardization processing: standardize all data to ensure consistency of data format and unit; Step S1026, establishing a knowledge graph data layer: based on the processed data, establishing a knowledge graph data layer for surrounding rock collapse risks during TBM tunnel construction.

6. The method for dynamic assessment of surrounding rock collapse risk during TBM tunnel construction driven by digital twins according to claim 1 is characterized by: The establishment and iterative optimization of the dynamic assessment model for surrounding rock collapse risk during TBM tunnel construction guided by the knowledge graph in step S103 specifically include: designing the framework of the dynamic assessment model and determining the assessment method based on the concepts and relationships defined in the knowledge graph; training the model using historical data and real-time data, evaluating the accuracy and reliability of the model through cross-validation methods, and continuously adjusting and optimizing it.

7. The method for dynamic assessment of surrounding rock collapse risk during TBM tunnel construction driven by digital twins according to claim 1 is characterized by: The dynamic assessment and early warning in step S104 specifically includes: continuously acquiring geological information, TBM equipment excavation parameters and operating status in the tunnel through real-time monitoring and data collection; inputting the processed data into a dynamic assessment model for immediate risk assessment; and automatically generating a landslide risk report based on the model's output results to identify potential risk areas and severity and issue early warnings.

8. An electronic device, characterized in that: The electronic device includes: a processor (210); and a memory (220) for storing one or more programs; When the one or more programs are executed by the processor (210), the processor is caused to execute the digital twin-driven dynamic assessment method for surrounding rock collapse risk in TBM tunnel construction as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by the processor (210), the method for dynamic assessment of surrounding rock collapse risk in TBM tunnel construction driven by a digital twin as described in any one of claims 1 to 7 is implemented.

Images