Multi-source data fusion comprehensive pipe gallery toughness evaluation method and system

Abstract

The invention discloses a multi-source data fusion comprehensive pipe gallery toughness evaluation method and system, and relates to the technical field of toughness evaluation, and the method comprises the steps: driving a GIS platform to carry out the geographic information collection according to the pipe gallery layout position of a to-be-evaluated pipe gallery, and obtaining the pipe gallery geographic information; performing building information retrieval to obtain pipe gallery building information; combining the pipe gallery building information and the pipe gallery geographic information to construct a pipe gallery multi-body dynamic model; performing associated pipe gallery positioning to obtain M associated pipe galleries, interacting with an IoT sensor to obtain M operation state time sequence data, performing disaster scene superposition matching, and outputting multi-element disaster intensity classification; and in the process of driving the pipe gallery multi-body dynamic model to carry out disaster simulation, collecting a multi-element structure response data set, carrying out pipe gallery toughness quantitative evaluation, and mapping and outputting a pipe gallery structure toughness cloud picture. The technical problem that the toughness of the comprehensive pipe gallery cannot be comprehensively evaluated in the prior art is solved, and the technical effect of dynamically and quantitatively evaluating the toughness of the pipe gallery is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of resilience assessment, and specifically to a comprehensive utility tunnel resilience assessment method and system based on multi-source data fusion. Background Art

[0002] As an intensive urban infrastructure, comprehensive utility tunnels have been widely used in the centralized laying and management of urban pipelines. However, with the expansion of the tunnel scale and the increase in the types of pipelines, the management and maintenance of comprehensive utility tunnels face huge challenges. Most of the existing tunnel resilience assessment methods rely on traditional single data sources, lacking real-time dynamic monitoring means and multi-dimensional disaster simulation analysis, resulting in insufficient accuracy in the resilience assessment of tunnels and being unable to effectively support disaster prevention and emergency response. Summary of the Invention

[0003] This application provides a comprehensive utility tunnel resilience assessment method and system based on multi-source data fusion, which is used to solve the technical problem that the prior art cannot comprehensively assess the resilience of comprehensive utility tunnels.

[0004] In view of the above problems, this application provides a comprehensive utility tunnel resilience assessment method and system based on multi-source data fusion.

[0005] In the first aspect of this application, a comprehensive utility tunnel resilience assessment method based on multi-source data fusion is provided. The method includes:

[0006] Driving a GIS platform to collect geographical information according to the layout position of the tunnel to be evaluated, so as to obtain tunnel geographical information, where the tunnel to be evaluated is a comprehensive utility tunnel; performing building information retrieval on the unique identifier of the tunnel to be evaluated to obtain tunnel building information; combining the tunnel building information and the tunnel geographical information to construct a tunnel multi-body dynamics model; performing associated tunnel positioning according to the layout position of the tunnel, and after obtaining M associated tunnels, obtaining M operation status time series data by interacting with M IoT sensors of the M associated tunnels; performing disaster scenario superposition matching according to the M operation status time series data to output a multi-disaster intensity classification; collecting a multi-source structure response data set during the process of driving the tunnel multi-body dynamics model to perform disaster simulation by using the multi-disaster intensity classification; performing a quantitative assessment of the tunnel resilience based on the multi-source structure response data set, and mapping and outputting a tunnel structure resilience cloud map.

[0007] In the second aspect of this application, a comprehensive utility tunnel resilience assessment system based on multi-source data fusion is provided. The system includes:

[0008] A geographic information acquisition module is used to drive a GIS platform to acquire geographic information according to the layout position of the culvert to be evaluated, so as to obtain culvert geographic information, where the culvert to be evaluated is a utility tunnel; a building information retrieval module is used to retrieve building information by using the unique identifier of the culvert to be evaluated to obtain culvert building information; a multi-body dynamics model construction module is used to construct a culvert multi-body dynamics model by combining the culvert building information and the culvert geographic information; an associated culvert positioning module is used to perform associated culvert positioning according to the layout position of the culvert, and after obtaining M associated culverts, M IoT sensors of the M associated culverts are interacted to obtain M operation state time series data; a disaster scenario superposition matching module is used to perform disaster scenario superposition matching according to the M operation state time series data and output a multi-disaster intensity grading; a disaster simulation module is used to collect a multi-structural response data set during the process of driving the culvert multi-body dynamics model to perform disaster simulation by using the multi-disaster intensity grading; a culvert resilience quantification evaluation module is used to perform culvert resilience quantification evaluation based on the multi-structural response data set and map and output a culvert structural resilience cloud map.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] In this application, a GIS platform is driven to acquire geographic information according to the layout position of the culvert to be evaluated, so as to obtain culvert geographic information, where the culvert to be evaluated is a utility tunnel; building information is retrieved by using the unique identifier of the culvert to be evaluated to obtain culvert building information; a culvert multi-body dynamics model is constructed by combining the culvert building information and the culvert geographic information; associated culvert positioning is performed according to the layout position of the culvert, and after obtaining M associated culverts, M IoT sensors of the M associated culverts are interacted to obtain M operation state time series data; disaster scenario superposition matching is performed according to the M operation state time series data and a multi-disaster intensity grading is output; a multi-structural response data set is collected during the process of driving the culvert multi-body dynamics model to perform disaster simulation by using the multi-disaster intensity grading; culvert resilience quantification evaluation is performed based on the multi-structural response data set and a culvert structural resilience cloud map is mapped and output. This invention solves the technical problem that the prior art cannot comprehensively evaluate the resilience of utility tunnels. By integrating GIS, BIM, and IoT technologies, and combining the superposition of disaster scenarios with multi-source data and multi-body dynamics model simulation, the technical effect of dynamically quantifying the evaluation of the resilience of culverts is achieved. Description of the Drawings

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0012] Figure 1 Schematic flow diagram of the comprehensive utility tunnel resilience assessment method for multi-source data fusion provided by the embodiments of the present application;

[0013] Figure 2 Schematic structural diagram of the comprehensive utility tunnel resilience assessment system for multi-source data fusion provided by the embodiments of the present application.

[0014] Explanation of reference numerals: Geographic information acquisition module 11, building information retrieval module 12, multi-body dynamics model construction module 13, associated utility tunnel positioning module 14, disaster scenario superposition and matching module 15, disaster simulation module 16, utility tunnel resilience quantitative assessment module 17. Detailed implementation manners

[0015] The present application provides a comprehensive utility tunnel resilience assessment method and system for multi-source data fusion, aiming to solve the technical problem that the prior art cannot comprehensively evaluate the resilience of utility tunnels. By integrating GIS, BIM, and IoT technologies, and combining the disaster scenario superposition of multi-source data and multi-body dynamics model simulation, the technical effect of dynamically quantifying the assessment of the resilience of utility tunnels is achieved.

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0017] It should be noted that any variations of the terms "including" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0018] Embodiment 1, as Figure 1 shown, the present application provides a comprehensive utility tunnel resilience assessment method for multi-source data fusion, and the method includes:

[0019] Step S100: Drive the GIS platform to collect geographical information according to the layout location of the corridor to be evaluated, so as to obtain the corridor geographical information, where the corridor to be evaluated is an integrated corridor.

[0020] In the embodiment of the present application, according to the layout location of the corridor to be evaluated, the geographical information system (GIS) platform is first driven to collect geographical information. Among them, the GIS platform is used to extract and process geographical information from the spatial data in the area where the corridor is located, and the layout location of the corridor to be evaluated is pre-determined. In this process, through the layout location of the corridor, the GIS platform obtains geographical data related to the corridor, such as terrain, landform, surrounding environment, and coordinate information of the specific location of the corridor. These data provide the necessary spatial background and infrastructure data for the subsequent evaluation of the corridor, ensuring that the geographical distribution and environmental characteristics of the corridor can be accurately reflected during the evaluation process. It should be emphasized that the corridor to be evaluated is an integrated corridor, that is, the centralized layout of various facilities such as pipelines, communications, and electricity, with a relatively complex structure. Therefore, accurate geographical information collection provides basic data for subsequent analysis.

[0021] By driving the GIS platform to collect geographical information, the corridor geographical information is obtained.

[0022] Step S200: Conduct a building information search using the unique identifier of the corridor to be evaluated to obtain the corridor building information.

[0023] In the embodiment of the present application, the building information is retrieved through the unique identifier of the corridor. The unique identifier of the corridor refers to the unique number or identification code of each corridor system, which is used to distinguish and identify different corridors. In practical applications, the unique identifier of the corridor is a combination of numbers or characters.

[0024] When conducting a building information search using the unique identifier of the corridor to be evaluated, access the building information database related to the corridor. The building information includes details such as the structural design, pipeline layout, material properties, and construction methods of the corridor. These information are stored in the building information model (BIM). By accessing the building information through the unique identifier of the corridor, the corridor building information of the corridor to be evaluated is retrieved, including the structural design, pipeline layout, material properties, etc. of the corridor. The obtained corridor building information is the initial corridor building information, and subsequent screening will be carried out to obtain the screened corridor building information.

[0025] Step S300: Combine the corridor building information and the corridor geographical information to construct a multi-body dynamics model of the corridor.

[0026] In the embodiment of the present application, when constructing a multi-body dynamics model of a utility tunnel by combining the utility tunnel building information and the utility tunnel geographic information, first, a plurality of key node coordinates are extracted from the layout position of the utility tunnel as driving conditions, the geographic information along the line is collected through a GIS platform, and the collected results are subjected to standardized coding to obtain the utility tunnel geographic information. Then, the initial building information is retrieved through the unique identifier of the utility tunnel, and the initial building information is screened according to the structural function of the utility tunnel to obtain the final utility tunnel building information; next, a benchmark multi-body dynamics model is constructed according to the mechanical characteristics of the utility tunnel, the building information and the geographic information of the utility tunnel are combined, and the combined result is input into the benchmark model and local adjustment is performed to finally obtain the multi-body dynamics model of the utility tunnel.

[0027] Further, in the method provided by the embodiment of the application, when constructing a multi-body dynamics model of a utility tunnel by combining the utility tunnel building information and the utility tunnel geographic information, it further includes:

[0028] Extracting a plurality of key node coordinates from the layout position of the utility tunnel; using the plurality of key node coordinates as driving conditions to drive the GIS platform to collect the geographic information along the utility tunnel to be evaluated, and after standardizing and coding the collected results, obtaining the utility tunnel geographic information; retrieving the initial building information by using the unique identifier of the utility tunnel, and screening the initial building information to obtain the utility tunnel building information by taking the utility tunnel structure function association as a constraint; constructing a benchmark multi-body dynamics model according to the mechanical characteristics of the utility tunnel, and taking the fusion result of the utility tunnel building information and the utility tunnel geographic information as input to localize the benchmark multi-body dynamics model to obtain the multi-body dynamics model of the utility tunnel.

[0029] In the embodiment of the present application, first, a plurality of key node coordinates are extracted from the layout position of the utility tunnel to be evaluated. These key nodes are pre-labeled, including the starting point, the ending point of the utility tunnel and the important position nodes along the line. These nodes are manually or automatically labeled through the utility tunnel planning drawings or GIS data and serve as the core reference points of the utility tunnel structure. Through this step, a plurality of key node coordinates along the utility tunnel are obtained.

[0030] Then, using the plurality of key node coordinates as driving conditions, the geographic information system (GIS) platform is driven to collect the geographic information along the utility tunnel. The GIS platform automatically extracts relevant information, such as terrain, landform, surrounding buildings, etc., from the spatial data of the area where the utility tunnel is located in combination with the preset coordinate points. Through this step, comprehensive geographic information along the utility tunnel is obtained, including terrain data and surrounding environment characteristics. Then, the collected geographic information is subjected to standardized coding processing. Through standardized coding, the information in different data systems is transformed to ensure that all geographic data can be processed under the same coordinate system and data structure. Through this step, the utility tunnel geographic information in a unified format is finally obtained.

[0031] After the standardization of geographical information, the unique identifier of the utility tunnel is used to retrieve building information. Through this identifier, the building information related to the utility tunnel is retrieved from the Building Information Modeling (BIM) database, and detailed building information related to the utility tunnel, that is, the initial building information, is obtained, including the structural design, pipeline layout, material properties, etc. of the utility tunnel. After obtaining the preliminary building information, relevant building information is screened according to the structural function association of the utility tunnel. Specifically, the structural function association of the utility tunnel includes the interaction relationships among various parts of the utility tunnel, such as the support structure, pipeline layout and bearing capacity, connections between pipelines, etc., and these information directly affect the overall function and resilience of the utility tunnel. In this step, first, by analyzing information such as the structural design drawings and pipeline layout plans of the utility tunnel, it is confirmed which building information is closely related to the actual function of the utility tunnel. By screening this information, the content unrelated to the assessment of the resilience of the utility tunnel is excluded, and finally, the building information of the utility tunnel is obtained, including the support structure, pipeline layout, bearing capacity, pipeline material, connection method, etc. of the utility tunnel.

[0032] Then, based on the mechanical properties of the utility tunnel, a reference multi-body dynamics model is constructed. The mechanical properties of the utility tunnel include the stiffness, elasticity, sealing performance, etc. of the pipeline. Combining these properties, through modeling methods such as finite element analysis (FEA), a model describing the dynamic response of the utility tunnel under different external forces is constructed. The reference model can simulate the performance of the utility tunnel under disaster conditions such as earthquakes and floods, providing the necessary data support for subsequent disaster simulation and resilience assessment.

[0033] Finally, the building information of the utility tunnel and the geographical information of the utility tunnel are combined and deeply integrated to eliminate potential data conflicts and inconsistencies. Through this integration process, it is ensured that the geographical environment and structural characteristics of the utility tunnel can be seamlessly combined, avoiding errors caused by data mismatch. The integrated data will be used as input to further localize the reference multi-body dynamics model. This process ensures that the model can accurately reflect the performance of the utility tunnel in a specific geographical environment by adjusting the node coordinates, physical parameters, and mechanical properties of the model. Through the localization adjustment, the multi-body dynamics model of the utility tunnel is finally obtained.

[0034] Furthermore, in the method provided by the application embodiment, a reference multi-body dynamics model is constructed according to the mechanical properties of the utility tunnel, and the fusion result of the building information of the utility tunnel and the geographical information of the utility tunnel is used as input to localize the reference multi-body dynamics model to obtain the multi-body dynamics model of the utility tunnel, and it further includes:

[0035] Extract the structural characteristics and dynamic characteristics of the utility tunnel from the utility tunnel building information; select a coupling modeling strategy based on the structural characteristics and dynamic characteristics of the utility tunnel; extract the component information, connection information, and attribute information of the utility tunnel from the utility tunnel building information; use the coupling modeling strategy as a technical constraint, and use the component information and connection information of the utility tunnel as geometric constraints to construct the reference multi-body dynamics model; through deep fusion of the attribute information and geographical information of the utility tunnel to eliminate data conflicts, and use the obtained fusion result as input to locally adjust the reference multi-body dynamics model to obtain the multi-body dynamics model of the utility tunnel.

[0036] In the embodiment of the present application, first, the structural characteristics and dynamic characteristics of the utility tunnel are extracted from the utility tunnel building information. Among them, the structural characteristics of the utility tunnel include geometric shape, support structure, pipeline layout, etc. The dynamic characteristics of the utility tunnel include stiffness, density, elastic modulus, etc.

[0037] Next, select a coupling modeling strategy based on the structural characteristics and dynamic characteristics of the utility tunnel. The selection of the coupling modeling strategy is mainly based on the mechanical behavior of the utility tunnel and the interaction between different components. For example, the mutual relationship between the stiffness of the pipeline and the support structure is a key modeling factor. Use numerical analysis methods such as finite element analysis (FEA) to decompose the utility tunnel into multiple small units and simulate the interaction between these small units.

[0038] Subsequently, extract the component information, connection information, and attribute information of the utility tunnel from the utility tunnel building information. The component information of the utility tunnel includes each physical part of the utility tunnel, such as pipelines, support structures, protective layers, etc., and these data are sourced from the component library in the BIM model. The connection information of the utility tunnel describes the connection methods between these components, such as welding, bolt connection, etc., obtained through topological analysis. The attribute information of the utility tunnel covers the properties of the materials used in the utility tunnel, such as elastic modulus, density, etc., obtained through the material database.

[0039] After that, use the coupling modeling strategy as a technical constraint, and use the component information and connection information of the utility tunnel as geometric constraints to construct the reference multi-body dynamics model. Specifically, use the previously selected coupling modeling strategy as a technical constraint, and combine the component information and connection information of the utility tunnel as geometric constraints to construct the reference multi-body dynamics model through the finite element modeling (FEA) method. The geometric constraints ensure that the relative positions and connection methods between the components of the utility tunnel are accurately reflected, and the coupling modeling strategy ensures that the interaction behavior of each part of the utility tunnel under force can be correctly simulated. Through this method, a reference multi-body dynamics model is finally obtained, which can simulate the dynamic response of the utility tunnel under external forces, including structural deformation, stress, and vibration, etc.

[0040] Finally, through the in-depth integration of the utility tunnel attribute information and the utility tunnel geographic information, data conflicts are eliminated, and the obtained integration result is used as the input to locally adjust the benchmark multi-body dynamics model. When deeply integrating the attribute information and geographic information of the utility tunnel, since these two types of data may have different coordinate systems, data formats, and precision differences, in-depth integration is carried out through technologies such as data cleaning, format conversion, and coordinate system unification. Specifically, first, the geographic data and attribute data from different data sources are standardized. For example, all geographic information is converted into a unified coordinate system to ensure the compatibility of different data sets. In addition, through a spatial matching algorithm, the attribute data is accurately docked with the corresponding geographic location to ensure that each component of the utility tunnel can be seamlessly combined with the actual geographical environment. Through this in-depth integration process, the conflicts and inconsistencies caused by differences in data sources are eliminated, and finally, a fused data set is obtained, which can seamlessly combine the structural information and geographic information of the utility tunnel.

[0041] Next, based on the data after in-depth integration, the benchmark multi-body dynamics model is locally adjusted. The local adjustment accurately adjusts the node coordinates and geometric shapes of the utility tunnel to ensure that the layout of the utility tunnel in the model is consistent with the actual geographical environment. For example, according to the terrain characteristics where the utility tunnel is located and the distribution of surrounding buildings, the positions of each node in the model are adjusted to make the model more in line with the real environment. Through local adjustment, the multi-body dynamics model of the utility tunnel is obtained.

[0042] Step S400: According to the layout position of the utility tunnel, perform associated utility tunnel positioning. After obtaining M associated utility tunnels, by interacting with the M IoT sensors of the M associated utility tunnels, M time-series operation state data are obtained.

[0043] In the embodiment of the present application, when performing associated utility tunnel positioning according to the layout position of the utility tunnel, first, a utility tunnel buffer area is determined. This area is a range with a preset buffer radius centered on the layout position of the utility tunnel. Then, all the utility tunnel information falling into this buffer area is collected to generate a buffer utility tunnel list containing these utility tunnels. On this basis, through the preset utility tunnel association rules, the buffer utility tunnel list is traversed to screen out M associated utility tunnels related to the utility tunnel to be evaluated. These associated utility tunnels refer to the utility tunnels that are geographically adjacent to, intersect with, or have other functional connections with the target utility tunnel. Then, real-time time-series operation state data from IoT sensors are collected from each of these M associated utility tunnels, including monitoring indicators such as temperature, humidity, strain, vibration, and displacement. Through this process, finally, the time-series operation state data of M utility tunnels are obtained.

[0044] Further, in the method provided by the application embodiment, after performing associated corridor positioning according to the corridor layout position and obtaining M associated corridors, by interacting with the M IoT sensors of the M associated corridors, M operation status time series data are obtained, and the method further includes:

[0045] Taking the corridor layout position as the center, generating a corridor buffer area that meets the preset buffer radius; collecting the corridor information falling into the corridor buffer area, and generating a buffer corridor list; traversing the buffer corridor list based on the preset corridor association rules, and screening out the M associated corridors; collecting the M operation status time series data from the M IoT sensors of the M associated corridors.

[0046] Further, the method provided by the application embodiment further includes:

[0047] The corridor association rules include intersection association, adjacent association, connection association, operation and maintenance association, and drainage association.

[0048] In the embodiment of the present application, first, taking the corridor layout position as the center, a corridor buffer area that meets the preset buffer radius is generated. The preset buffer radius is preset by technical experts. In this process, a corridor buffer area is generated by using the buffer analysis function in the Geographic Information System (GIS) according to the preset buffer radius. The buffer area is an area drawn around the position of the target corridor within a specified radius range, and is used to determine the corridors adjacent to the target corridor. This buffer area is generated through spatial data analysis technology (such as the buffer analysis tool provided in ArcGIS or QGIS), and can accurately identify the corridors falling within this area. Through this method, all surrounding corridors are obtained, ensuring that all corridors that may be related to the target corridor are considered in the subsequent steps, and an area containing the information of all corridors within the buffer area is obtained.

[0049] Then, through spatial query technology and a Database Management System (DBMS), all corridor information is collected from the buffer area, and a buffer corridor list is generated. This step extracts the corridor information that meets the buffer range from the database by using the SQL query language, and extracts information such as the geometric shape, layout direction, and pipeline type of the pipeline, so as to generate a buffer corridor list.

[0050] Then, the buffer corridor list is filtered based on the preset corridor association rules. The corridor association rules include intersection association (i.e., the corridors have an intersection in space), adjacent association (i.e., the corridors are geographically adjacent to each other), connection association (i.e., the corridors are connected by pipelines or other connecting parts), operation and maintenance association (i.e., the corridors have an intersection or share facilities in daily operation and maintenance), and drainage association (i.e., sharing a drainage system). Through spatial analysis methods (such as topological analysis, geometric matching analysis, etc.), the eligible corridors are screened out from the buffer corridor list according to these rules. The spatial analysis method determines whether they meet the preset rules by calculating the spatial relationships between corridors (such as corridor intersections, distances, adjacency relationships, etc.). Finally, M associated corridors are obtained through screening.

[0051] Finally, through an interactive Internet of Things (IoT) sensor data acquisition method, the time-series operation status data of the corridors are collected from the IoT sensors of the M associated corridors. The IoT sensors are devices installed in the corridors for real-time monitoring of parameters such as temperature, humidity, strain, vibration, and displacement of the corridors. One IoT sensor is deployed on each associated corridor, and through data acquisition, M time-series operation status data are obtained.

[0052] Furthermore, in the method provided by the application embodiment, before performing disaster scenario overlay matching based on the M time-series operation status data and outputting the multi-disaster intensity grading, it further includes:

[0053] Interactively obtain multiple disaster preconditions of multiple earthquake disaster levels in the earthquake disaster mode, where the disaster preconditions include pre-temperature characteristics, pre-humidity characteristics, pre-strain characteristics, and pre-vibration characteristics; call the multiple peak ground accelerations of the multiple earthquake disaster levels; associatively store the multiple earthquake disaster levels, multiple disaster preconditions, and multiple peak ground accelerations to complete the construction of the earthquake disaster mode map; and so on, construct the flood disaster mode map and the explosion disaster mode map; aggregate the earthquake disaster mode map, the flood disaster mode map, and the explosion disaster mode map to complete the construction of the preset disaster mode library.

[0054] In the embodiment of the present application, first, through interactive data acquisition, multiple disaster preconditions related to the earthquake disaster mode are extracted from the historical database, and these characteristics include pre-temperature characteristics, pre-humidity characteristics, pre-strain characteristics, and pre-vibration characteristics. Among them, the pre-temperature characteristics include temperature fluctuations inside and outside the corridor, day-night temperature differences, seasonal temperature differences, etc.; the pre-humidity characteristics refer to the change situation of the humidity inside the corridor; the pre-strain characteristics include the minute deformations or stresses sensed in the corridor before the disaster occurs; and the pre-vibration characteristics refer to the vibration frequency and amplitude inside the corridor.

[0055] Next, the peak ground accelerations of multiple earthquake disaster levels are called. These data reflect the maximum acceleration of ground vibration under different earthquake intensities. The peak ground acceleration is usually obtained by earthquake monitoring equipment (such as accelerometers) or earthquake data platforms, and the data comes from historical earthquake records or real-time earthquake monitoring systems. The calling process accesses the earthquake monitoring data platform through a data interface or API, and obtains the corresponding peak acceleration data according to different earthquake disaster levels. Through this process, the peak ground accelerations of multiple earthquake disaster levels are obtained.

[0056] Subsequently, multiple earthquake disaster levels, multiple pre-disaster characteristics, and multiple peak ground accelerations are associated and stored. This process is completed by a database management system (DBMS). All the extracted data is stored in a unified database, and data association and table design are used to ensure that the relationships between different disaster levels, pre-disaster characteristics, and peak accelerations are accurately recorded. Through data indexing and efficient querying, these associated data can be quickly accessed and analyzed, providing support for disaster simulation and early warning. Finally, a comprehensive earthquake disaster pattern atlas is obtained, which shows the relationships between different earthquake disaster levels, pre-disaster characteristics, and peak ground accelerations, providing a basis for disaster simulation.

[0057] Similarly, flood disaster pattern atlases and explosion disaster pattern atlases are constructed according to the same method. These atlases consider the pre-disaster characteristics and intensities of floods and explosions respectively, and corresponding disaster patterns are constructed through time series data analysis.

[0058] Finally, the earthquake disaster pattern atlas, flood disaster pattern atlas, and explosion disaster pattern atlas are aggregated to complete the construction of the preset disaster pattern library.

[0059] Step S500: Perform disaster scenario overlay matching based on the M running state time series data, and output a multi-disaster intensity classification.

[0060] In the embodiment of the present application, when performing disaster scenario overlay matching based on the M running state time series data, first, data alignment based on timestamps is performed on the M running state time series data to ensure data synchronization in time. Then, the aligned data is segmented using a preset time window, and the extreme value data within each time window is extracted through the window extreme state extraction method. Subsequently, using these window state extreme value data, the preset disaster pattern library is traversed to calculate the similarity, and the disaster type - level characteristics corresponding to each group of data are output according to the similarity. Finally, the disaster type - level characteristics are feature-aggregated to obtain the final multi-disaster intensity classification, which includes different levels of peak ground acceleration, flood water level, and explosion shock pressure.

[0061] Further, in the method provided by the application embodiment, when performing disaster scenario superposition matching based on the M running state time series data and outputting a multi-disaster intensity classification, it further includes:

[0062] Align the M running state time series data based on timestamps to obtain M aligned state time series data; after dividing the M aligned state time series data by a preset time window, extract window extreme state values to obtain M groups of window state extreme value data; use the M groups of window state extreme value data to traverse the preset disaster mode library for similarity calculation and output M groups of disaster type - level features; perform feature aggregation on the M groups of disaster type - level features to obtain the multi-disaster intensity classification, where the multi-disaster intensity classification includes multi-level seismic peak acceleration, multi-level flood water level, and multi-level explosion shock pressure.

[0063] In the embodiment of the present application, first, align the M running state time series data based on timestamps. A timestamp refers to the time mark when data is collected. Through alignment, it is ensured that each group of data is synchronized at the same time interval. Use a time alignment algorithm, such as an interpolation method or time window clipping, to uniformly process sensor data from different sources, solve the time misalignment problem caused by different data collection frequencies or inconsistent sensor times, and ensure that subsequent data analysis is not affected by time series deviation, obtaining M aligned state time series data.

[0064] Subsequently, divide the M aligned state time series data by a preset time window. Use a sliding window algorithm. By setting an appropriate window size (such as every 10 minutes), each aligned state time series data is divided into multiple time periods to ensure that the time variation of the data can be refined. Then, through window extreme state extraction, the maximum and minimum values are extracted from each time window as representatives of the state within the window. These extreme values can reflect the key changes within that time period, such as the highest temperature point, the lowest strain point, etc. Finally, M groups of window state extreme value data are obtained through this process.

[0065] Subsequently, calculate the similarity between the obtained M sets of window state extreme value data and the preset disaster mode library. The disaster mode library contains characteristic data of various disaster types (such as earthquakes, floods, explosions, etc.) under different disaster intensities, including typical environmental changes and structural responses during the occurrence of disasters. Through similarity calculations (such as Euclidean distance, cosine similarity, etc.), compare the window state extreme value data with the known disaster scenarios in the disaster mode library, calculate the similarity between each set of window state data and different disaster types in the disaster mode library, and output the disaster type - level characteristics for each set of data according to the similarity calculation results, that is, the corresponding disaster type (such as earthquake, flood, explosion) and its intensity level (such as mild, moderate, severe) of the data. These disaster types and levels reflect the possible response degrees of the utility tunnel or facilities under specific disaster scenarios.

[0066] Finally, perform feature aggregation on the M sets of disaster type - level characteristics. Through the feature aggregation method, synthesize the characteristics of each set of disaster type and level into a unified evaluation result. In this process, through combined analysis, indicators such as the peak acceleration of earthquakes, the water level of floods, and the shock pressure of explosions are combined into a multi - disaster intensity classification. These indicators are respectively divided into different levels according to the standard disaster intensity classification system. Specifically, the peak acceleration of earthquakes is divided into mild, moderate, and severe, the flood water level can also be divided into low water level, medium water level, and high water level, and the explosion shock pressure can be divided into weak, medium, and strong according to the intensity. Through these standardized classifications, a comprehensive multi - disaster intensity classification is finally obtained, which covers multiple levels of earthquake peak acceleration, multiple levels of flood water level, and multiple levels of explosion shock pressure.

[0067] Step S600: During the process of driving the multi - body dynamics model of the utility tunnel for disaster simulation using the multi - disaster intensity classification, collect a multi - variable structure response data set.

[0068] In the embodiment of the present application, first, through the preset structure identification rule, locate multiple ductility risk key points in the multi - body dynamics model of the utility tunnel. These key points are the parts of the utility tunnel that are most vulnerable to being affected during the occurrence of disasters. Subsequently, based on the multi - disaster intensity classification, perform multi - disaster coupling simulation to simulate the comprehensive impact of different types of disasters (such as earthquakes, floods, explosions, etc.) on the utility tunnel, and obtain K sets of coupled disaster test data, which reflect the multiple responses of the utility tunnel under different disaster intensities. Then, use these coupled disaster test data to drive the multi - body dynamics model of the utility tunnel for disaster simulation. During the simulation process, collect multiple sets of structure response data located at the ductility risk key points. These response data include structural reactions such as strain, vibration, and displacement of the utility tunnel under different disaster scenarios, and finally form a multi - variable structure response data set.

[0069] Further, in the method provided by the application embodiments, during the process of driving the multi-body dynamics model of the utility tunnel for disaster simulation by using the multi-disaster intensity grading, a multi-structural response data set is collected, and it further includes:

[0070] Preset a structural identification rule, and locate multiple resilience risk key points in the multi-body dynamics model of the utility tunnel according to the structural identification rule; perform multi-disaster coupling simulation on the multi-disaster intensity grading to obtain K coupled disaster test data; during the process of driving the multi-body dynamics model of the utility tunnel for disaster simulation by using the K coupled disaster test data, collect multiple groups of structural response data of the multiple resilience risk key points, where the multiple groups of structural response data constitute the multi-structural response data set.

[0071] In the embodiments of the present application, first, through a preset structural identification rule, the parts that need to be monitored key points in the utility tunnel structure are determined. The structural identification rule is based on the analysis of the design parameters, functional requirements, and historical data of the utility tunnel, combined with structural reliability analysis and finite element analysis (FEA) to evaluate the key parts of the utility tunnel. These rules consider the load path, structural connection parts, support system, and potential failure modes of the utility tunnel to identify which parts may be most severely damaged during a disaster. Especially for disasters such as earthquakes, floods, and explosions, by analyzing the stress distribution and structural deformation of the utility tunnel, the parts that are most vulnerable to damage under different disaster conditions are identified. Once these structural identification rules are set, multiple resilience risk key points are located in the multi-body dynamics model of the utility tunnel according to these rules. The multi-body dynamics model of the utility tunnel is constructed based on dynamic simulation and structural mechanics modeling, considering factors such as the geometric shape of the utility tunnel, support system, pipe type, and material properties. In this model, the response of the utility tunnel during a disaster is simulated through mechanical simulation. By comparing with historical disaster data, the key positions in the utility tunnel that are most vulnerable to disasters are identified, and these positions are marked as resilience risk key points. For example, these key points may be pipe connections, turning parts, support frames, and important pipe intersections, etc. Through this process, multiple resilience risk key points are obtained.

[0072] Next, based on the multi-disaster intensity grading, multi-disaster coupling simulation is performed. This process uses multi-physics field coupling simulation technology (such as simulation software like ANSYS). Multi-physics field coupling means considering the effects of multiple physical phenomena simultaneously in the same model, such as simultaneously simulating the vibration caused by an earthquake, the water level change of a flood, and the impact pressure generated by an explosion, etc. By setting the intensities of different disasters (such as the peak acceleration of an earthquake, flood water level, and explosion impact pressure, etc.), different disaster mode input data are generated. Using numerical solution methods (such as the finite element method or boundary element method), these disaster factors are coupled to simulate their comprehensive effects on the utility tunnel structure. Through this process, K coupled disaster test data are generated.

[0073] During the simulation process, K sets of coupled disaster test data are used as input to drive the multi-body dynamics model of the utility tunnel. The multi-body dynamics model is a technology based on structural dynamics and mechanical modeling, which takes into account factors such as the stiffness, mass distribution, and support method of the utility tunnel, as well as dynamic responses such as vibrations and deformations caused by disasters. Through dynamic simulation and nonlinear analysis, the behavior of the utility tunnel under the action of disasters is simulated, and the structural responses of the utility tunnel under different disaster scenarios are calculated. During this process, data is collected from multiple calibrated key points of resilience risk and their responses are recorded, such as strain (tensile or compressive of materials caused by deformation), vibration (frequency and amplitude caused by the action of disasters), displacement (position change of pipelines or structural components), etc. Finally, these multiple sets of structural response data collected from the key points of resilience risk are summarized to form a multi-structural response dataset.

[0074] Step S700: Based on the multi-structural response dataset, perform a quantitative assessment of the resilience of the utility tunnel, and map and output a resilience cloud map of the utility tunnel structure.

[0075] In the embodiment of the present application, when performing a quantitative assessment of the resilience of the utility tunnel based on the multi-structural response dataset, first, a physics-informed neural network that has been pre-trained is used to perform resilience quantification on the multi-structural response dataset. The specific method is to process the multi-group structural response data of multiple key points of resilience risk to obtain corresponding resilience quantification RGB values. These RGB values represent the structural resilience levels of the utility tunnel under different disaster scenarios. Then, according to the K sets of coupled disaster test data, these resilience quantification RGB values are divided into K groups of resilience quantification RGB values, with each group corresponding to a different disaster scenario and intensity. Then, based on the positions of the key points of resilience risk, these grouped resilience quantification RGB values are mapped into the multi-body dynamics model of the utility tunnel through linear interpolation to complete the resilience assessment of each part of the utility tunnel. Finally, through this process, a resilience cloud map of the utility tunnel structure is obtained.

[0076] Furthermore, in the method provided by the embodiment of the application, when performing a quantitative assessment of the resilience of the utility tunnel based on the multi-structural response dataset and mapping and outputting a resilience cloud map of the utility tunnel structure, it further includes:

[0077] Quantify the multi-group structural response data of the multiple key points of resilience risk through a physics-informed neural network to obtain multiple groups of resilience quantification RGB values; divide the multiple groups of resilience quantification RGB values into K groups of resilience quantification RGB values according to the K sets of coupled disaster test data; based on the multiple key points of resilience risk, linearly interpolate and map the K groups of resilience quantification RGB values to the multi-body dynamics model of the utility tunnel to obtain the resilience cloud map of the utility tunnel structure.

[0078] In the embodiments of the present application, first, a physics-informed neural network is used to quantify multiple sets of structural response data of multiple resilience risk key points to obtain corresponding resilience quantification RGB values. Among them, the physics-informed neural network is a pre-trained deep learning model. By learning a large amount of historical data, it can combine physical laws to predict the structural response of the utility tunnel under different disaster conditions. During training, the input data of the network includes the structural response data from each resilience risk key point, and the output is the resilience value corresponding to the structural response data. This resilience value represents the structural resilience level of the utility tunnel in a specific disaster scenario. The higher the value, the stronger the resilience, and the lower the value, the weaker the resilience. Among them, these training data are obtained from the historical database, and the resilience values corresponding to the structural response data are pre-annotated by technical experts.

[0079] By inputting multiple sets of structural response data of multiple resilience risk key points into the physics-informed neural network, multiple resilience values are obtained. Then, according to a preset rule, the resilience values are quantified into RGB values. Each RGB value corresponds to a specific color, which is used to represent different structural resilience levels. Among them, the low-resilience area (i.e., the area with a lower resilience value) is assigned red, indicating that this area is prone to damage in disasters; the high-resilience area is assigned green, indicating that this area can better withstand the impact of disasters.

[0080] Next, according to the K sets of coupled disaster test data, the obtained multiple sets of resilience quantification RGB values are grouped. The coupled disaster test data are obtained through multi-disaster coupling simulation, which represents the combined impact of different types of disasters (such as earthquakes, floods, explosions, etc.) on the utility tunnel. Through these test data, the resilience quantification RGB values are grouped according to the disaster type and intensity, so as to ensure that each group of RGB values can reflect the resilience performance of the utility tunnel under a specific disaster intensity. Specifically, these RGB values are divided into K sets of resilience quantification RGB values according to different disaster scenarios, and each group corresponds to a specific disaster mode.

[0081] Finally, based on the positions of multiple resilience risk key points, a linear interpolation method is used to map the K sets of resilience quantification RGB values to the multi-body dynamics model of the utility tunnel. In this process, each group of resilience quantification RGB values is smoothly extended from the key point positions to the overall structural model of the utility tunnel. In this way, each part of the utility tunnel will be assigned a corresponding resilience value and show different responses during disasters. Finally, a structural resilience cloud map of the utility tunnel is generated, which clearly shows the resilience level of the utility tunnel under different disaster scenarios through the change of colors.

[0082] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0083] This application drives the GIS platform to collect geographical information according to the layout position of the corridor to be evaluated, so as to obtain the corridor geographical information, where the corridor to be evaluated is an integrated corridor; retrieves the building information of the corridor by using the unique identifier of the corridor to be evaluated, so as to obtain the corridor building information; constructs a multi-body dynamics model of the corridor by combining the corridor building information and the corridor geographical information; locates the associated corridors according to the layout position of the corridor, and after obtaining M associated corridors, obtains M time-series operation state data by interacting with the M IoT sensors of the M associated corridors; performs disaster scenario superposition matching according to the M time-series operation state data, and outputs a multi-disaster intensity classification; in the process of driving the multi-body dynamics model of the corridor to perform disaster simulation by using the multi-disaster intensity classification, collects a multi-source structural response data set; performs quantitative evaluation of the corridor resilience based on the multi-source structural response data set, and maps and outputs a corridor structure resilience cloud map. The present invention solves the technical problem that the prior art cannot comprehensively evaluate the resilience of an integrated corridor, and through integrating GIS, BIM and IoT technologies, combining the disaster scenario superposition of multi-source data and the simulation of the multi-body dynamics model, achieves the technical effect of dynamically quantifying the evaluation of the corridor resilience.

[0084] Embodiment 2, based on the same inventive concept as the integrated corridor resilience evaluation method with multi-source data fusion in the foregoing embodiment, as Figure 2 shown, this application provides an integrated corridor resilience evaluation system with multi-source data fusion. The system in the embodiment of this application and the method embodiment are based on the same inventive concept. Among them, the system includes:

[0085] A geographical information collection module 11, configured to drive the GIS platform to collect geographical information according to the layout position of the corridor to be evaluated, so as to obtain the corridor geographical information, where the corridor to be evaluated is an integrated corridor; a building information retrieval module 12, configured to retrieve the building information of the corridor by using the unique identifier of the corridor to be evaluated, so as to obtain the corridor building information; a multi-body dynamics model construction module 13, configured to construct a multi-body dynamics model of the corridor by combining the corridor building information and the corridor geographical information; an associated corridor positioning module 14, configured to locate the associated corridors according to the layout position of the corridor, and after obtaining M associated corridors, obtain M time-series operation state data by interacting with the M IoT sensors of the M associated corridors; a disaster scenario superposition matching module 15, configured to perform disaster scenario superposition matching according to the M time-series operation state data, and output a multi-disaster intensity classification; a disaster simulation module 16, configured to collect a multi-source structural response data set in the process of driving the multi-body dynamics model of the corridor to perform disaster simulation by using the multi-disaster intensity classification; a corridor resilience quantitative evaluation module 17, configured to perform quantitative evaluation of the corridor resilience based on the multi-source structural response data set, and map and output a corridor structure resilience cloud map.

[0086] Further, the system is also used to implement the following functions:

[0087] Extract multiple key node coordinates from the laying position of the pipe gallery; use the multiple key node coordinates as driving conditions to drive the GIS platform to collect geographical information along the pipe gallery to be evaluated, and then obtain the pipe gallery geographical information by performing standardized coding on the collection results; use the unique identifier of the pipe gallery to retrieve building information, and after obtaining the initial building information, screen the pipe gallery building information from the initial building information with the constraint of the pipe gallery structure-function association; construct a benchmark multi-body dynamics model according to the mechanical characteristics of the pipe gallery, and use the fusion result of the pipe gallery building information and the pipe gallery geographical information as input to localize the benchmark multi-body dynamics model to obtain the pipe gallery multi-body dynamics model.

[0088] Further, the system is also used to implement the following functions:

[0089] Generate a pipe gallery buffer area that meets the preset buffer radius with the laying position of the pipe gallery as the center; collect the pipe gallery information falling into the pipe gallery buffer area to generate a buffer pipe gallery list; traverse the buffer pipe gallery list based on the preset pipe gallery association rules to screen out the M associated pipe galleries; collect the M operation status time series data from the M IoT sensors of the M associated pipe galleries.

[0090] Further, the system is also used to implement the following functions:

[0091] Interactively obtain multiple disaster preconditions of multiple earthquake disaster levels in the earthquake disaster mode, where the disaster preconditions include pre-temperature characteristics, pre-humidity characteristics, pre-strain characteristics, and pre-vibration characteristics; call the multiple peak ground accelerations of the multiple earthquake disaster levels; associate and store the multiple earthquake disaster levels, multiple disaster preconditions, and multiple peak ground accelerations to complete the construction of the earthquake disaster mode map; and so on, construct the flood disaster mode map and the explosion disaster mode map; aggregate the earthquake disaster mode map, the flood disaster mode map, and the explosion disaster mode map to complete the construction of the preset disaster mode library.

[0092] Further, the system is also used to implement the following functions:

[0093] Perform data alignment on the M running state time series data based on timestamps to obtain M aligned state time series data; after dividing the M aligned state time series data using a preset time window, extract window extreme state values to obtain M sets of window state extreme value data; use the M sets of window state extreme value data to traverse the preset disaster mode library for similarity calculation and output M sets of disaster type - level features; perform feature aggregation on the M sets of disaster type - level features to obtain the multi - disaster intensity classification, where the multi - disaster intensity classification includes multi - level seismic peak acceleration, multi - level flood water level, and multi - level explosion shock pressure.

[0094] Furthermore, the system is also used to implement the following functions:

[0095] Preset a structure identification rule and locate multiple key points of ductility risk in the multi - body dynamics model of the pipe gallery according to the structure identification rule; perform multi - disaster coupling simulation on the multi - disaster intensity classification to obtain K sets of coupled disaster test data; during the process of driving the multi - body dynamics model of the pipe gallery to conduct disaster simulation using the K sets of coupled disaster test data, collect multiple sets of structural response data of the multiple key points of ductility risk, where the multiple sets of structural response data constitute the multi - disaster structural response data set.

[0096] Furthermore, the system is also used to implement the following functions:

[0097] Quantify the multiple sets of structural response data of the multiple key points of ductility risk through a physics - informed neural network to obtain multiple sets of ductility - quantified RGB values; divide the multiple sets of ductility - quantified RGB values into K sets of ductility - quantified RGB values according to the K sets of coupled disaster test data; map the K sets of ductility - quantified RGB values to the multi - body dynamics model of the pipe gallery using linear interpolation based on the multiple key points of ductility risk to obtain the ductility cloud map of the pipe gallery structure.

[0098] Furthermore, the system is also used to implement the following functions:

[0099] The pipe gallery association rules include intersection association, adjacent association, connection association, operation and maintenance association, and drainage association.

[0100] Furthermore, the system is also used to implement the following functions:

[0101] The structural characteristics and dynamic characteristics of the utility tunnel are extracted from the utility tunnel building information; a coupling modeling strategy is selected according to the structural characteristics and dynamic characteristics of the utility tunnel; the component information, connection information, and attribute information of the utility tunnel are extracted from the utility tunnel building information; the coupling modeling strategy is used as a technical constraint, and the component information and connection information of the utility tunnel are used as geometric constraints to construct the reference multi-body dynamics model; by deeply fusing the attribute information and geographical information of the utility tunnel to eliminate data conflicts, and using the obtained fusion result as input, the reference multi-body dynamics model is locally adjusted to obtain the multi-body dynamics model of the utility tunnel.

[0102] It should be noted that the above-mentioned sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification has been made. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0103] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0104] This specification and the drawings are only exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A comprehensive duct gallery resilience assessment method for multi-source data fusion, characterized in that, The method includes: Driving a GIS platform to collect geographic information according to the layout position of the corridor to be evaluated, so as to obtain the corridor geographic information, wherein the corridor to be evaluated is an integrated corridor; Performing building information retrieval on the unique identifier of the corridor to be evaluated to obtain the corridor building information; Combining the corridor building information and the corridor geographic information to construct a multi-body dynamics model of the corridor; Performing associated corridor positioning according to the layout position of the corridor. After obtaining M associated corridors, M IoT sensors of the M associated corridors are interacted to obtain M time series data of the operating states; Performing disaster scenario superposition matching according to the M time series data of the operating states, and outputting a multi-disaster intensity classification; During the process of driving the multi-body dynamics model of the corridor to perform disaster simulation by using the multi-disaster intensity classification, a multi-structural response data set is collected; Performing quantitative evaluation of the corridor resilience based on the multi-structural response data set, and mapping and outputting a corridor structure resilience cloud map.

2. The comprehensive pipe gallery resilience assessment method for multi-source data fusion according to claim 1, wherein Combining the corridor building information and the corridor geographic information to construct a multi-body dynamics model of the corridor. The method includes: Extracting multiple key node coordinates from the layout position of the corridor; Using the multiple key node coordinates as driving conditions to drive the GIS platform to collect geographic information along the corridor to be evaluated, and after standardizing and coding the collection results, obtaining the corridor geographic information; Performing building information retrieval by using the unique identifier of the corridor to obtain initial building information, and then screening the corridor building information from the initial building information with the constraint of the corridor structure function association; Constructing a benchmark multi-body dynamics model according to the mechanical characteristics of the corridor, and using the fusion result of the corridor building information and the corridor geographic information as input to localize the benchmark multi-body dynamics model to obtain the multi-body dynamics model of the corridor.

3. The comprehensive pipe gallery resilience assessment method for multi-source data fusion according to claim 1, characterized in that, Performing associated corridor positioning according to the layout position of the corridor. After obtaining M associated corridors, M IoT sensors of the M associated corridors are interacted to obtain M time series data of the operating states. The method includes: Taking the layout position of the corridor as the center, generating a corridor buffer area that meets the preset buffer radius; Collecting the corridor information falling into the corridor buffer area to generate a buffer corridor list; Traversing the buffer corridor list based on the preset corridor association rules to screen out the M associated corridors; Collecting the M time series data of the operating states from the M IoT sensors of the M associated corridors.

4. The comprehensive utility tunnel resilience assessment method for multi-source data fusion according to claim 3, wherein, Before performing disaster scenario superposition matching according to the M time series data of the operating states and outputting a multi-disaster intensity classification, the method includes: Interactively obtaining multiple disaster preconditions of multiple earthquake disaster levels in the earthquake disaster mode, wherein the disaster preconditions include pre-temperature characteristics, pre-humidity characteristics, pre-strain characteristics, and pre-vibration characteristics; Invoking the multiple peak ground accelerations of the multiple earthquake disaster levels; Associatively storing the multiple earthquake disaster levels, multiple disaster preconditions, and multiple peak ground accelerations to complete the construction of the earthquake disaster mode atlas; And so on, constructing a flood disaster mode atlas and an explosion disaster mode atlas; Aggregate the earthquake disaster pattern atlas, flood disaster pattern atlas, and explosion disaster pattern atlas to complete the construction of a preset disaster pattern library.

5. The comprehensive duct gallery resilience assessment method for multi-source data fusion according to claim 4, characterized in that, Perform disaster scenario overlay matching based on the M running state time series data and output a multi-hazard intensity grading. The method includes: Align the M running state time series data based on timestamps to obtain M aligned state time series data; After dividing the M aligned state time series data using a preset time window, extract window extreme state values to obtain M sets of window state extreme data; Use the M sets of window state extreme data to traverse the preset disaster pattern library for similarity calculation and output M sets of disaster type - grade characteristics; Aggregate the characteristics of the M sets of disaster type - grade characteristics to obtain the multi-hazard intensity grading, where the multi-hazard intensity grading includes multi-level earthquake peak accelerations, multi-level flood water levels, and multi-level explosion shock pressures.

6. The comprehensive duct gallery resilience assessment method for multi-source data fusion according to claim 5, characterized in that, During the process of driving the multi-body dynamics model of the utility tunnel for disaster simulation using the multi-hazard intensity grading, collect a multi-structural response data set. The method includes: Preset a structure identification rule and locate multiple ductility risk key points in the multi-body dynamics model of the utility tunnel according to the structure identification rule; Perform multi-hazard coupling simulation on the multi-hazard intensity grading to obtain K coupled disaster test data; During the process of driving the multi-body dynamics model of the utility tunnel for disaster simulation using the K coupled disaster test data, collect multiple sets of structural response data of the multiple ductility risk key points, where the multiple sets of structural response data constitute the multi-structural response data set.

7. The comprehensive duct gallery resilience evaluation method for multi-source data fusion according to claim 6, characterized in that Perform quantitative assessment of the ductility of the utility tunnel based on the multi-structural response data set and map and output a ductility cloud map of the utility tunnel structure. The method includes: Quantify the multiple sets of structural response data of the multiple ductility risk key points through a physics-informed neural network to obtain multiple sets of ductility quantification RGB values; Divide the multiple sets of ductility quantification RGB values into K sets of ductility quantification RGB values according to the K coupled disaster test data; Based on the multiple ductility risk key points, linearly interpolate and map the K sets of ductility quantification RGB values to the multi-body dynamics model of the utility tunnel to obtain the ductility cloud map of the utility tunnel structure.

8. The comprehensive utility tunnel resilience assessment method for multi-source data fusion according to claim 3, characterized in that The utility tunnel association rules include intersection association, adjacent association, connection association, operation and maintenance association, and drainage association.

9. The comprehensive utility tunnel resilience assessment method for multi-source data fusion according to claim 2, wherein, Construct a benchmark multi-body dynamics model according to the mechanical characteristics of the utility tunnel, and use the fusion result of the utility tunnel building information and utility tunnel geographical information as input to localize the benchmark multi-body dynamics model to obtain the multi-body dynamics model of the utility tunnel. The method includes: Extract the tunnel structure characteristics and tunnel dynamic characteristics from the tunnel building information; Select a coupling modeling strategy according to the tunnel structure characteristics and tunnel dynamic characteristics; Extract tunnel component information, tunnel connection information, and tunnel attribute information from the tunnel building information; Use the coupling modeling strategy as a technical constraint and the tunnel component information and tunnel connection information as geometric constraints to construct the benchmark multi-body dynamics model; By deeply integrating the utility tunnel attribute information and the utility tunnel geographic information to eliminate data conflicts, and using the obtained integration result as input to locally adjust the benchmark multi-body dynamics model, the utility tunnel multi-body dynamics model is obtained.

10. An integrated utility tunnel resilience assessment system for multi-source data fusion, characterized in that, The system includes: A geographic information acquisition module, configured to drive a GIS platform to acquire geographic information according to the layout position of the utility tunnel to be evaluated, so as to obtain the utility tunnel geographic information, where the utility tunnel to be evaluated is an integrated utility tunnel; A building information retrieval module, configured to retrieve building information using the unique identifier of the utility tunnel to be evaluated, so as to obtain the utility tunnel building information; A multi-body dynamics model construction module, configured to construct a utility tunnel multi-body dynamics model by combining the utility tunnel building information and the utility tunnel geographic information; An associated utility tunnel positioning module, configured to perform associated utility tunnel positioning according to the layout position of the utility tunnel, and after obtaining M associated utility tunnels, obtain M operation status time series data by interacting with M IoT sensors of the M associated utility tunnels; A disaster scenario superposition matching module, configured to perform disaster scenario superposition matching according to the M operation status time series data, and output a multi-disaster intensity classification; A disaster simulation module, configured to collect a multi-structural response data set during the process of driving the utility tunnel multi-body dynamics model to perform disaster simulation using the multi-disaster intensity classification; A utility tunnel resilience quantification evaluation module, configured to perform utility tunnel resilience quantification evaluation based on the multi-structural response data set, and map and output a utility tunnel structure resilience cloud map.

Images