Historic block pipe gallery and ancient building safety collaborative early warning system based on digital twinning

Abstract

The application discloses a historical block pipe gallery and ancient building safety collaborative early warning system based on digital twinning, belongs to the technical field of cultural relic protection and municipal facility safety monitoring, and comprises a twinning model construction, a coupling threshold modeling and a safety collaborative control module. Through collection of drawings and surveying and mapping data of the pipe gallery and the ancient building, an integrated three-dimensional basic model is built, monitoring point selection binding and data mapping correction are completed; relying on the twinning model, spatial correlation points are screened, a coupling relationship model is constructed to sort out a risk transmission path, a structure safety grade is evaluated, and a hierarchical dynamic early warning threshold system is built; abnormal points are determined, a risk transmission path is located, and targeted collaborative regulation is executed, and after regulation, iteration is updated to form a complete control closed loop; the problems of traditional separate modeling, fuzzy risk analysis and non-closed loop control are effectively solved, and safety collaborative early warning and integrated control of historical block pipe gallery operation and maintenance and ancient building structure protection can be realized.

Description

Technical Field

[0001] This invention belongs to the field of cultural relic protection and municipal facility safety monitoring technology, specifically involving a collaborative early warning system for the safety of historical block utility tunnels and ancient buildings based on digital twins. Background Technology

[0002] The coordinated management of utility tunnel operation and maintenance and ancient building protection in historical districts has attracted much attention. Currently, the methods mostly adopt separate facility modeling, manual monitoring, and fixed threshold early warning, which have shortcomings such as disconnect between model data, vague risk assessment, and lack of closed-loop management, making it difficult to meet actual safety management needs. Therefore, this invention urgently needs to solve the following technical problems:

[0003] The separate modeling of utility tunnels and ancient buildings makes it impossible to integrate spatial structural relationships, the layout of monitoring points lacks scientific basis, and the data and physical models are difficult to match synchronously, thus failing to provide a reliable basis for safety analysis.

[0004] The risk transmission pattern of utility tunnel operation to ancient buildings is difficult to clarify, the safety level assessment method is simplistic, the early warning threshold cannot be dynamically adjusted with the environment, and the early warning results are not practical enough.

[0005] The lack of targeted and collaborative handling solutions for safety anomalies, coupled with the absence of iterative mechanisms for models, data, and early warning standards after handling, makes it impossible to form a closed-loop management system and continuously ensure the safety of facilities and cultural relics. To address this, we propose a collaborative early warning system for the safety of historical district utility tunnels and ancient buildings based on digital twins. Summary of the Invention

[0006] The purpose of this invention is to provide a collaborative early warning system for the safety of historical district utility tunnels and ancient buildings based on digital twins, so as to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a collaborative early warning system for the safety of historical district utility tunnels and ancient buildings based on digital twins, comprising:

[0008] Twin model construction module: acquire drawings and survey data of historical block corridors and ancient buildings, construct an integrated three-dimensional basic model; set up virtual monitoring points and select and determine actual monitoring points, and associate and bind them with the model; collect structural safety monitoring data and encode and map it, trigger model correction through data fitting and deviation judgment, and form an integrated digital twin basic model and time-series monitoring dataset.

[0009] Coupled threshold modeling module: Screening spatial correlation point pairs between utility tunnel and ancient building and constructing spatial correlation matrix, combining parameter pairs and calculating correlation degree to obtain strongly correlated parameter pairs; sorting out risk transmission path and constructing coupling relationship model; calculating parameter deviation degree and point safety index to assess structural safety level, and constructing and dynamically correcting graded dynamic early warning threshold system;

[0010] Safety collaborative management module: It compares structural safety monitoring parameters with early warning thresholds to determine the early warning level and identify abnormal trigger points; it locates related points and risk transmission paths, formulates and executes targeted collaborative control; after control, it updates the digital twin model and time series dataset, iteratively corrects the coupled model and early warning thresholds, and forms a safety collaborative management closed loop.

[0011] Preferably, the specific process of obtaining drawings and survey data of historical district utility tunnels and ancient buildings, and constructing an integrated three-dimensional basic model is as follows:

[0012] Obtain historical district utility tunnel layout drawings and ancient building structure drawings, and simultaneously collect surveying data of the utility tunnels and ancient buildings;

[0013] Using a BIM modeling platform, the dimensional deviations were corrected based on the utility tunnel drawings and on-site survey data. Three-dimensional model units of the main structure and auxiliary components of the utility tunnel were drawn, material parameters were entered and spliced ​​for verification, and a three-dimensional solid model of the utility tunnel was formed.

[0014] Based on ancient architectural drawings and survey data, the shape and connection method of structural components are restored, three-dimensional model units are drawn, material parameters are entered and spliced ​​according to structural logic to form a three-dimensional solid model of the ancient building.

[0015] Collect geospatial information of historical blocks and determine a unified spatial coordinate system. Import the two types of models into the coordinate system, align the coordinates with the pre-embedded fixed points as the reference, correct the overlapping areas of the models, complete the spatial fusion, and form an integrated three-dimensional basic model.

[0016] Preferably, the specific process of setting up virtual monitoring points, selecting and determining actual monitoring points, and associating and binding them with the model is as follows:

[0017] Virtual monitoring points are evenly deployed throughout the entire area of ​​the utility tunnel and the entire area of ​​the ancient building. Based on the historical structural safety monitoring data of the main body corresponding to each virtual monitoring point, statistical feature values ​​are extracted as structural safety correlation parameters. Preset weight coefficients are assigned to each structural safety correlation parameter, and after normalization and dimensionless processing, the risk assessment value of the virtual point is obtained by weighted calculation.

[0018] The risk assessment value is compared with the preset threshold. If the value meets the standard, it is marked as an actual monitoring point and the corresponding monitoring equipment is installed. The spatial coordinates of the actual monitoring point are collected and imported into the integrated three-dimensional basic model. The corresponding structural components are located through the coordinate comparison algorithm, and the association and binding between the actual monitoring point and the model components are completed by coordinate matching.

[0019] Preferably, the specific process of collecting structural safety monitoring data, encoding and mapping it, triggering model correction through data fitting and deviation judgment, and forming an integrated digital twin basic model and time-series monitoring dataset is as follows:

[0020] Structural safety monitoring parameters are collected in real time by monitoring equipment deployed at actual monitoring points, and the raw monitoring data is preprocessed. The preprocessed structural safety monitoring parameters are encoded according to preset rules and synchronously transmitted to the integrated three-dimensional basic model.

[0021] The model update time step is preset. Within each step, the corresponding time series monitoring dataset is retrieved, the structural safety monitoring parameters are linearly fitted, and the real-time fitted monitoring values ​​and the fitting slope are extracted.

[0022] The initial health status benchmark parameters and benchmark slope of the structural safety monitoring parameters are determined, the numerical deviation and trend deviation are calculated, and the comprehensive deviation value of the structural status is obtained after normalization.

[0023] If the overall deviation value of the structural state meets the standard, the model mapping parameter correction process is triggered: the deviation value range is matched to obtain the overall deviation value correction coefficient, and the model mapping parameters of the corresponding points and parameters in the integrated three-dimensional basic model are updated according to the correction coefficient to form an integrated digital twin basic model;

[0024] The data from each monitoring point are organized by timestamp to construct a time-series monitoring dataset that includes parameter type, real-time fitted monitoring value, timestamp, point code, and model correction record.

[0025] Preferably, the specific process of screening spatially related point pairs between utility tunnels and ancient buildings, constructing a spatial relationship matrix, combining parameter pairs, and calculating the relationship degree to obtain strongly related parameter pairs is as follows:

[0026] Based on the integrated digital twin basic model, the actual monitoring points of the utility tunnel and the actual monitoring points of the ancient buildings that are spatially adjacent or connected to it are extracted.

[0027] Calculate the three-dimensional spatial distance between points, and combine the structural hierarchy to retain the point combinations at the same level or on the force transmission chain to determine the spatially related point pairs of the utility tunnel and ancient buildings.

[0028] Using the associated point pair as rows and columns and the three-dimensional spatial distance as elements, a point spatial association matrix is ​​constructed; the structural safety monitoring parameters of the utility tunnel and the ancient building in the associated point pair are combined in pairs to form a utility tunnel-ancient building structural safety monitoring parameter pair.

[0029] The time series of real-time fitted monitoring values ​​is retrieved, and the correlation degree of parameters is calculated using the time series cross-correlation analysis algorithm. Parameter pairs with a correlation degree greater than a preset threshold are marked as strongly correlated parameter pairs.

[0030] Preferably, the specific process of identifying risk transmission paths and constructing a coupling relationship model is as follows:

[0031] Based on the spatial correlation points of the pipe gallery-ancient building corresponding to the strongly correlated parameter pairs, the time-series lag correlation analysis is used to determine the direction of influence transmission between parameters.

[0032] Strongly correlated parameters with continuous transmission relationships are connected in series in the transmission order to form a one-way risk transmission path from changes in the operation parameters of the utility tunnel to the response of the structural parameters of the ancient building.

[0033] Using the spatial correlation matrix of points as the basis of spatial constraints, strong correlation parameter pairs as the core of parameter correlation, and risk transmission path as the dynamic change logic, the three types of data are integrated according to the topological structure to construct a coupling relationship model between the operation status of the utility tunnel and the structural response of the ancient building.

[0034] Preferably, the specific process of calculating parameter deviation and location safety index to assess structural safety level, and constructing and dynamically correcting a graded dynamic early warning threshold system is as follows:

[0035] Retrieve the initial health status baseline parameters of each structure safety monitoring parameter at the actual monitoring points, and calculate the deviation of the parameter current status;

[0036] Preset multiple deviation threshold ranges for each parameter and match the level coefficients. Match the deviation with the threshold ranges to obtain the corresponding level coefficients.

[0037] By combining the level coefficients of each parameter with the preset weight coefficients, the overall safety index of the actual monitoring point is calculated. The safety index is then matched with the preset level range to determine the structural safety level of the point.

[0038] Based on the time-series monitoring dataset and structural safety level, multiple initial warning thresholds are preset for each parameter. An environmental impact dynamic correction model is constructed to dynamically correct the initial thresholds, forming a three-level dynamic warning threshold for each parameter. Finally, a hierarchical dynamic safety warning threshold system covering the entire domain and all parameters is constructed.

[0039] Preferably, the specific process of comparing structural safety monitoring parameters with early warning thresholds to determine the early warning level and identify the abnormal trigger point is as follows:

[0040] Based on the full-domain, full-parameter hierarchical dynamic early warning threshold system, the structural safety monitoring parameters of each actual monitoring point are compared with the corresponding dynamic early warning thresholds of each level for that point and parameter, and the early warning level of the corresponding monitoring point is determined according to the threshold level exceeded by the parameter.

[0041] When any structural safety monitoring parameter at an actual monitoring point exceeds any level of dynamic early warning threshold, that point is designated as an abnormal trigger monitoring point, and the corresponding early warning level is recorded simultaneously.

[0042] Preferably, the specific process of locating related points and risk transmission paths, and formulating and implementing targeted and coordinated regulation is as follows:

[0043] Based on the abnormal trigger monitoring points, and based on the coupling relationship model between the operation status of the utility tunnel and the structural response of the ancient building, we extract the corresponding pairs of spatially related points of the utility tunnel and the ancient building, as well as the pairs of strongly related parameters corresponding to the abnormal parameters, and screen the associated actual monitoring points according to the risk transmission path.

[0044] Taking the abnormal trigger monitoring points as the core control objects, and combining their structural safety level, early warning level, risk transmission path and related actual monitoring points, a safety collaborative control plan is formulated to determine the control objects and control processes.

[0045] The quantitative value of the control intensity is calculated and matched with the corresponding control intensity level. The results are integrated to form a collaborative control instruction and sent to the operation and maintenance management terminal, which then executes the targeted operation and maintenance control.

[0046] Preferably, the specific process of updating the digital twin model and time-series dataset after regulation, iteratively correcting the coupled model and early warning threshold, and forming a closed loop of safe collaborative management and control is as follows:

[0047] After the control is completed, the structural safety monitoring parameters of each actual monitoring point are collected and preprocessed. The preprocessed data is then synchronously transmitted to the integrated digital twin basic model, and the model mapping parameters of the corresponding points and parameters are updated according to the model mapping parameter correction process.

[0048] The data is added to the time-series monitoring dataset in timestamp order to complete the update; the parameter correlation is recalculated based on the updated dataset, the strongly correlated parameter pairs and risk transmission paths are updated, and the coupling relationship model is iteratively corrected.

[0049] By combining updated monitoring data with structural safety levels, the environmental correction factor is recalculated, and the graded dynamic early warning threshold is optimized.

[0050] Through the cyclical execution of the entire process, a closed loop of safety collaborative management is formed, realizing the safety collaborative early warning and integrated management of utility tunnels and ancient buildings in historical districts.

[0051] Compared with the prior art, the beneficial effects of the present invention are:

[0052] (1) The historical block utility tunnel and ancient building safety collaborative early warning system based on digital twins integrates the structural form and spatial connection relationship of the two types of facilities by building an integrated three-dimensional model of the utility tunnel and ancient buildings, thus abandoning the traditional separate modeling mode; relying on historical monitoring data to conduct risk assessment, reasonably select monitoring points and bind them to the model, and dynamically optimize the model parameters after sorting and analyzing the data collected on site to form continuous time-series monitoring data, effectively solving the problems of traditional point layout without basis and data disconnection from physical model, and providing a practical basic support for facility safety risk analysis.

[0053] (2) The historical block utility tunnel and ancient building safety collaborative early warning system based on digital twins sorts out the risk transmission path between the utility tunnel and the ancient building by constructing a coupling relationship model, and clearly grasps the impact law of the operation of the utility tunnel on the structure of the ancient building; the safety level of the point is evaluated based on the parameter status, and the early warning threshold is adjusted in combination with the changes in the on-site environment, which makes up for the defects of the traditional risk assessment being vague, the safety assessment method being single, and the early warning standard being fixed, making the safety assessment and early warning work more suitable for the operation and maintenance and protection needs of the historical block.

[0054] (3) The historical block utility tunnel and ancient building safety collaborative early warning system based on digital twin can quickly locate abnormal points through a hierarchical dynamic early warning system, formulate targeted collaborative control plans in combination with risk transmission paths, and deal with safety hazards in a timely manner. After control, the digital twin model, monitoring data and early warning threshold are updated simultaneously to form a complete control process of monitoring-early warning-control-optimization. It can not only respond quickly to safety issues, but also make the system continuously adapt to the actual situation on site, providing a stable and long-term safety guarantee for the operation of historical block utility tunnels and the protection of ancient buildings. Attached Figure Description

[0055] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] Example 1;

[0058] Please see Figure 1 This invention provides a digital twin-based collaborative early warning system for the safety of historical street utility tunnels and ancient buildings, including: a twin model construction module, a coupling threshold modeling module, and a safety collaborative management and control module;

[0059] The digital twin model construction module acquires drawings and survey data of historical street utility tunnels and ancient buildings to construct an integrated 3D basic model; it sets up virtual monitoring points and selects and determines actual monitoring points, associating and binding them with the model; it collects structural safety monitoring data and encodes and maps it, triggering model correction through data fitting and deviation judgment, forming an integrated digital twin basic model and a time-series monitoring dataset. The specific process is as follows:

[0060] Obtain the layout drawings of the utility tunnels in the historical district and the architectural structure drawings of the ancient buildings. At the same time, obtain the survey data of the utility tunnels and ancient buildings, including: the spatial dimensions, spatial location, component material parameters, and main structure material parameters of each component of the utility tunnels and ancient buildings.

[0061] Using a general BIM modeling platform, based on the utility tunnel layout drawings, and comparing the on-site survey data, the dimensional deviations between the drawings and the actual site were corrected. Three-dimensional model units of the main structure of the utility tunnel (utility tunnel body, utility tunnel foundation, utility tunnel supports, etc.) and auxiliary components (valves, inspection channels, drainage devices, etc.) were drawn one by one. The collected utility tunnel material parameters were entered into the corresponding three-dimensional model units. The model units were spliced ​​together according to the actual layout sequence of the utility tunnel. After parameter verification (comparing the model parameters with the on-site survey data to ensure that the deviation is within the allowable range), the three-dimensional solid model of the utility tunnel was assembled.

[0062] Based on the architectural drawings of ancient buildings and combined with on-site survey data, the actual form and connection method of each structural component (walls, beams, columns, foundations, etc.) of the ancient buildings are restored one by one according to the structural composition of the ancient buildings, and the corresponding three-dimensional model units are drawn. After data verification, the collected material parameters of the ancient buildings are entered into the corresponding three-dimensional model units. The component models are assembled according to the structural logic of the ancient buildings (load-bearing logic and structural layout, such as the order from foundation to beams and columns, and then to walls) to complete the assembly of the three-dimensional solid model of the ancient buildings.

[0063] Geospatial information of the entire historical district was collected. A general plane coordinate system suitable for urban cultural relic area surveying was selected as the unified spatial coordinate system. Both the 3D solid model of the utility tunnel and the 3D solid model of the ancient building were imported into this unified coordinate system. Pre-embedded fixed points at the connection between the utility tunnel and the foundation of the ancient building were selected as spatial reference points (these points were marked during the on-site survey and are shared fixed points for both the utility tunnel and the ancient building). The reference point coordinates of the 3D solid models of the utility tunnel and the ancient building were aligned with the reference coordinates in the unified spatial coordinate system. The overlapping areas of the models were corrected and pre-processed (trimming, deviation correction, etc.). The spatial splicing and fusion of the two types of models were completed to form an integrated 3D basic model of the historical district's utility tunnel and ancient building (the construction method of the integrated 3D basic model of the historical district's utility tunnel and ancient building is the existing method, and the process is not described).

[0064] Virtual monitoring points were evenly distributed across the entire area of ​​the utility tunnel and the entire area of ​​the ancient buildings. For each virtual monitoring point, statistical feature values ​​were extracted based on the historical structural safety monitoring data of the corresponding main structure, serving as structural safety correlation parameters; where:

[0065] The structural safety associated parameters corresponding to the virtual monitoring points of the utility tunnel include: the average historical structural deformation, the peak historical pipeline operating pressure, and the frequency of historical water leakage.

[0066] The structural safety parameters associated with the virtual monitoring points of ancient buildings include: the average width of historical cracks, the cumulative amount of historical foundation settlement, and the average tilt angle of historical structures.

[0067] For each virtual monitoring point, the structural safety-related parameters are assigned a preset weight coefficient (the weight coefficient is set according to the degree of influence of each parameter on the safety of the corresponding main structure), and after normalization and dimensionless processing, a weighted calculation is performed to obtain the risk assessment value of the virtual point.

[0068] A risk assessment threshold for virtual monitoring points is preset. The risk assessment value of the virtual point is compared with the corresponding preset threshold. If it is greater than or equal to the corresponding preset threshold, the virtual point is marked as an actual monitoring point, and monitoring equipment corresponding to the monitoring needs is installed at the actual monitoring point.

[0069] A total station is used to obtain the actual spatial coordinates of all actual monitoring points. The spatial coordinates of each actual monitoring point are imported into an integrated three-dimensional basic model. The structural component corresponding to each coordinate is located by a coordinate comparison algorithm. Each actual monitoring point is associated and bound to the corresponding component of the model by a one-to-one coordinate matching method to complete the association configuration.

[0070] Furthermore, the specific process of locating the structural component corresponding to each coordinate through the coordinate comparison algorithm is as follows: the spatial coordinates of the actual monitoring point are matched and calculated with the coordinate information of each structural component in the integrated three-dimensional basic model, the spatial position deviation between the two is compared, and the component with the deviation within a preset reasonable range is selected as the structural component corresponding to the monitoring point.

[0071] The structural safety monitoring parameters of each actual monitoring point are collected in real time using monitoring equipment installed at each point.

[0072] The parameters collected at each actual monitoring point in the utility tunnel include: leakage data, structural deformation data, and pipeline operating pressure data.

[0073] The parameters collected at each actual monitoring point of the ancient building include: crack width data, foundation settlement data, structural tilt angle data, etc.

[0074] The collected raw monitoring data were preprocessed, including: outliers were removed using the 3σ criterion and missing values ​​were filled in using linear interpolation to ensure data validity;

[0075] Each set of preprocessed structural safety monitoring parameters is coded according to the rule of monitoring area + main body type + point number, and transmitted to the integrated 3D basic model in real time; (the code corresponds one-to-one with the model mapping node identifier, and the model maps the data to the corresponding model mapping node through code matching).

[0076] The model update time step is preset. For each actual monitoring point, within each update time step, the time series monitoring dataset corresponding to various structural safety monitoring parameters of that monitoring point is retrieved.

[0077] For each type of structural safety monitoring parameter, the linear fitting formula y=kt+b is used for data fitting, where: y is the fitted monitoring value of the structural safety monitoring parameter, t is the continuous time node within the time step, k is the fitting slope, and b is the intercept.

[0078] Extract the real-time fitted monitoring values ​​(i.e., the fitting results corresponding to the last time node of the update time step) and the fitting slope of the structural safety monitoring parameters within the current update time step;

[0079] The field survey parameters corresponding to the current structural safety monitoring parameter type, entered during the integrated 3D basic model construction phase, are used as the initial health status benchmark parameters for the structural safety monitoring parameters; the slope of the monitoring parameters obtained by fitting the initial field survey data is used as the initial health status benchmark slope for the structural safety monitoring parameters.

[0080] The deviations of the real-time fitted monitoring values ​​of the structural safety monitoring parameters within the current update time step from the initial health state baseline parameters, and the deviations of the fitted slope from the initial health state baseline slope, are calculated respectively using the following formulas:

[0081] ,in, This is the real-time fitted monitoring value of the structural safety monitoring parameters at the current update time step. These are the initial health status baseline parameters corresponding to the structural safety monitoring parameters. This represents numerical deviation;

[0082] The slope of the fitted structural safety monitoring parameters within the current update time step. The initial health status baseline slope for structural safety monitoring parameters. This indicates a trend deviation.

[0083] After normalizing and dimensionlessly removing the numerical and trend deviations of the structural safety monitoring parameters at the current update time step, substitute them into the formula: The comprehensive deviation value of the structural state corresponding to the structural safety monitoring parameters at the current update time step is obtained. ;in, and Preset weighting coefficients;

[0084] A preset structural state comprehensive deviation threshold is set. If the structural state comprehensive deviation value corresponding to the update time step is greater than or equal to the preset threshold, it is determined that the structural state of the monitored part of the physical entity deviates from the initial healthy state and an abnormal change occurs, triggering the model mapping parameter correction process, specifically:

[0085] Several structural safety monitoring parameters and comprehensive deviation value ranges for structural status are set, and a comprehensive deviation value correction coefficient is preset for each comprehensive deviation value range. Among them, the larger the upper and lower limits of the comprehensive deviation value range of the structural state, the larger the positive correction coefficient of the comprehensive deviation;

[0086] The comprehensive deviation value of the structural state corresponding to the structural safety monitoring parameter that triggers the correction process is matched with the comprehensive deviation value range of all structural states corresponding to the structural safety monitoring parameter type, and the corresponding comprehensive deviation value correction coefficient is output. ;

[0087] In the integrated 3D basic model, the model mapping parameters corresponding to the monitoring point and the structural safety monitoring parameter type are corrected using the following formula:

[0088] ,in, These are the corrected model mapping parameters;

[0089] After the model mapping parameters are corrected, a digital twin basic model integrating the historical block corridor and ancient buildings that can be dynamically updated is thus formed.

[0090] All monitoring data from each monitoring point are organized in chronological order by timestamp to form a complete time-series monitoring dataset that includes monitoring parameter types, real-time fitted monitoring values, timestamps, point codes, and model correction records.

[0091] It should be noted that building an integrated three-dimensional basic model of the utility tunnel and ancient buildings, which integrates the structural forms and spatial connection relationships of the two types of facilities, can comprehensively reflect the overall layout of the utility tunnel and ancient buildings in the historical district, and provide a realistic model basis for subsequent spatial correlation analysis and risk transmission assessment.

[0092] Determining actual monitoring points based on historical structural safety monitoring data and deploying monitoring equipment in conjunction with risk assessment results helps to rationally allocate monitoring resources, focus monitoring on areas prone to safety hazards, and improve the overall targeting of monitoring work.

[0093] Encoding and mapping the monitoring data, performing linear fitting and deviation analysis, and dynamically adjusting the model mapping parameters based on the analysis results can ensure that the digital twin model continuously matches the actual state of the physical entity, reduce the disconnect between the model and the entity's state, and maintain the model's practical reference value.

[0094] This generates a time-series monitoring dataset containing information such as parameter types, real-time fitted monitoring values, and timestamps. It completely preserves monitoring data and model correction records from different time periods, providing detailed and continuous data support for subsequent coupling relationship modeling, safety level assessment, early warning threshold setting, and coordinated control execution, ensuring that the operation of subsequent stages of the system has a reliable data basis.

[0095] The coupling threshold modeling module: filters spatially related point pairs between utility tunnels and ancient buildings and constructs a spatial correlation matrix; combines parameter pairs and calculates the correlation degree to obtain strongly correlated parameter pairs; it identifies risk transmission paths and constructs a coupling relationship model; it calculates parameter deviation and point safety index to assess structural safety levels; and it constructs and dynamically corrects a graded dynamic early warning threshold system. The specific process is as follows:

[0096] Based on the integrated digital twin basic model, all actual monitoring points of the utility tunnels are extracted, as well as the actual monitoring points of ancient buildings that have spatial adjacency or basic connection with the actual monitoring points of each utility tunnel.

[0097] Using the Euclidean distance formula, the three-dimensional spatial distance between each set of actual monitoring points of the extracted utility tunnel and the corresponding actual monitoring points of the ancient building is calculated. At the same time, considering the structural level to which the points belong (utility tunnel foundation / ancient building foundation, utility tunnel body / ancient building wall), only the combination of points at the same level or on the force transmission chain (including: combination of utility tunnel foundation and ancient building foundation, combination of utility tunnel body and ancient building wall) is retained, and the combination of points across structural levels is excluded.

[0098] The selected point combinations are marked as spatially related point pairs of the utility tunnel and ancient buildings.

[0099] Using the pairs of spatially related points between the utility tunnel and the ancient building as rows and columns, and the three-dimensional spatial distance between the points as matrix elements, a spatial relationship matrix of points is constructed.

[0100] For each pair of spatially associated points of the utility tunnel and ancient building in the spatial correlation matrix, all structural safety monitoring parameters of the actual monitoring points of the utility tunnel in the pair are combined with all structural safety monitoring parameters of the corresponding actual monitoring points of the ancient building to obtain several sets of parameter combinations. Each set of parameter combinations is marked as a pair of structural safety monitoring parameters of the utility tunnel and ancient building.

[0101] For each pair of pipe gallery-ancient building structural safety monitoring parameters, the real-time time-series fitted monitoring value sequences of the two types of parameters are retrieved from the time-series monitoring dataset. The time-series cross-correlation analysis algorithm is used to calculate the correlation degree between the parameters. The calculation formula is as follows:

[0102] ,

[0103] in:

[0104] Let be the correlation degree of the i-th group of pipe gallery-ancient building structural safety monitoring parameter pair;

[0105] For the i-th parameter pair, the real-time fitted monitoring value of the structural safety monitoring parameter corresponding to the actual monitoring point of the pipe gallery at the t-th time node;

[0106] For the i-th parameter pair, the real-time fitted monitoring value of the structural safety monitoring parameter corresponding to the actual monitoring point of the ancient building at the t-th time node;

[0107] and These are the time-series average values ​​of safety monitoring parameters for the utility tunnel structure and the ancient building structure, respectively.

[0108] t represents the time node identifier of the time series data;

[0109] n is the total number of time nodes for the time-series monitoring data;

[0110] A preset parameter correlation threshold is set, and the pipe gallery-ancient building structural safety monitoring parameter pairs with a correlation greater than the preset threshold are marked as strongly correlated parameter pairs;

[0111] Based on the spatially related point pairs corresponding to strongly correlated parameter pairs, time-lag correlation analysis is used to determine the direction of influence transmission between parameters.

[0112] Strongly correlated parameters with continuous transmission relationships are connected in series in the transmission order to form a one-way risk transmission path from changes in the operation parameters of the utility tunnel to the response of the structural parameters of the ancient building.

[0113] Furthermore, the specific process of determining the direction of influence transmission between parameters using time-lag correlation analysis is as follows:

[0114] For each pair of strongly correlated parameters, the real-time time-series fitted monitoring value sequence of the safety monitoring parameters of the utility tunnel structure and the safety monitoring parameters of the ancient building structure is retrieved from the time-series monitoring dataset.

[0115] The safety monitoring parameter sequence of the utility tunnel structure is subjected to lag processing at different lag steps, and the correlation coefficient between the lag parameter sequence of the utility tunnel and the safety monitoring parameter sequence of the ancient building structure is calculated at each lag step.

[0116] If the correlation coefficient at a certain lag step is the maximum value among all test steps, and the absolute value of the correlation coefficient is greater than or equal to the previously preset parameter correlation threshold and the sign is positive, then it is determined that the change of the safety monitoring parameter of the utility tunnel structure precedes the change of the safety monitoring parameter of the ancient building structure, and the direction of influence transmission is from the utility tunnel parameter to the ancient building parameter.

[0117] Based on the above judgment results, the direction of influence transmission for each pair of strongly correlated parameters is clarified;

[0118] Using the spatial correlation matrix of points as the spatial constraint basis, strong correlation parameter pairs as the core of parameter correlation, and risk transmission path as the dynamic change logic, the three types of data are integrated according to the topological structure of spatial location nodes - parameter correlation attributes - risk transmission edges to construct a coupling relationship model between the operation status of the utility tunnel and the structural response of ancient buildings. In this model, actual monitoring points are used as nodes, structural safety monitoring parameters are used as node attributes, and risk transmission paths are used as node connection edges, which can quantitatively reflect the impact law and transmission path of changes in the operation status of the utility tunnel on the structural safety of ancient buildings.

[0119] For each structural safety monitoring parameter at each actual monitoring point, retrieve the corresponding initial health status benchmark parameter (from step one). Using the initial health status benchmark parameter as a reference, calculate the deviation of the current state of the structural safety monitoring parameter. The calculation formula is as follows:

[0120] ,

[0121] in:

[0122] The state deviation of the p-th structural safety monitoring parameter;

[0123] This is the real-time fitted monitoring value of the structural safety monitoring parameters at the current time point;

[0124] These are the initial health status baseline parameters corresponding to the safety monitoring parameters of this structure;

[0125] (In conjunction with national and industry standards for the safe operation of utility tunnels and the protection of ancient building structures) for each structural safety monitoring parameter at each actual monitoring point, multiple levels of deviation threshold ranges are preset separately, and corresponding level coefficients are matched for each level range;

[0126] The deviation of each structural safety monitoring parameter is matched with all corresponding preset threshold intervals, and the corresponding level coefficient is output.

[0127] For each actual monitoring point, the overall safety index of that monitoring point is calculated by combining the level coefficients corresponding to the structural safety monitoring parameters at that point. The calculation formula is as follows:

[0128] ,

[0129] Where: S represents the overall safety index of the actual monitoring point;

[0130] The level coefficient corresponding to the p-th structural safety monitoring parameter in the actual monitoring points;

[0131] The preset weighting coefficients are the corresponding structural safety monitoring parameters of the p-th item in the actual monitoring points;

[0132] p represents the serial number of the structural safety monitoring parameter at the actual monitoring point;

[0133] m represents the total number of structural safety monitoring parameters at the actual monitoring points;

[0134] For each actual monitoring point, several structural safety levels are preset separately, and each structural safety level corresponds to a specific overall safety index level range for that point.

[0135] The overall safety index of each actual monitoring point is matched with the overall safety index level range corresponding to that point, and the structural safety level corresponding to each actual monitoring point is output.

[0136] For each structural safety monitoring parameter at each actual monitoring point, based on historical data from the time-series monitoring dataset and structural safety level assessment results, multiple initial warning thresholds are preset; an environmental impact dynamic correction model is constructed to dynamically correct the initial warning thresholds, and the correction formula is as follows:

[0137] ,

[0138] in:

[0139] The p-th structural safety monitoring parameter is the k-th level dynamic early warning threshold. Let the p-th structural safety monitoring parameter be the k-th level initial warning threshold; The environmental correction coefficient for the k-th level threshold of the p-th structural safety monitoring parameter; This represents the current environmental parameter value. The corresponding historical average environmental parameter value; k is the warning threshold level identifier;

[0140] Furthermore, the process of obtaining environmental correction coefficients is as follows: Based on the time series data of historical environmental parameters and the time series data of structural safety monitoring parameters, linear regression analysis is used to calculate the correlation coefficient between environmental parameters and monitoring parameters, and the calculated correlation coefficient is used as the environmental correction coefficient for the corresponding parameter and the corresponding level threshold.

[0141] After the threshold correction is completed, a unique three-level dynamic early warning threshold is formed for each structural safety monitoring parameter at each actual monitoring point, and finally a full-domain, full-parameter, hierarchical, and dynamic safety early warning threshold system is constructed.

[0142] It should be noted that by relying on the integrated digital twin model and combining spatial location and structural hierarchy to screen the connection points between the utility tunnel and the ancient building, it is possible to comprehensively sort out the spatial connection and stress relationship between the two types of facilities, providing an analytical basis that fits the actual scenario for subsequent risk transmission analysis.

[0143] By performing correlation calculations and determining the transmission direction of structural safety monitoring parameters, a coupling relationship model can be built, which can better present the connection between changes in the operating status of the utility tunnel and the structural response of the ancient building, help clarify the transmission path of potential risks, and provide a reference for the source assessment of safety risks.

[0144] The deviation of parameters is calculated with the initial health status as a reference, and the safety index of the location is obtained by combining the weight coefficients. Then, the structural safety level is evaluated, which can distinguish the safety status of different monitoring points and provide a reference for subsequent graded early warning and differentiated management.

[0145] By combining historical data with environmental impact to construct dynamic early warning thresholds, the thresholds can be adaptively adjusted according to changes in the on-site environment, making the early warning standards more in line with actual operating conditions and helping to improve the rationality and applicability of early warning results.

[0146] This module provides the data and model foundation for the construction of the twin model, and also provides evaluation standards and early warning basis for subsequent safety collaborative management and control, so that the analysis, evaluation and early warning links of the entire system form a coherent logic, and better adapt to the safety monitoring and protection needs of historical district corridors and ancient buildings.

[0147] The safety collaborative management module compares structural safety monitoring parameters with early warning thresholds to determine the early warning level and identify anomaly trigger points; it locates related points and risk transmission paths, formulates and executes targeted collaborative control; after control, it updates the digital twin model and time-series dataset, iteratively corrects the coupled model and early warning thresholds, and forms a closed loop for safety collaborative management. The specific process is as follows:

[0148] Based on the full-domain, full-parameter hierarchical dynamic early warning threshold system constructed in (step two), the structural safety monitoring parameters of each actual monitoring point are compared with the corresponding dynamic early warning thresholds of each level for that point and parameter in turn. The early warning level of the corresponding monitoring point is determined according to the threshold level exceeded by the parameter.

[0149] When any structural safety monitoring parameter at an actual monitoring point exceeds any level of dynamic early warning threshold, the point is identified as an abnormal trigger monitoring point, and the corresponding early warning level is recorded simultaneously.

[0150] Based on the abnormal trigger monitoring point, and based on the coupling relationship model between the operation status of the utility tunnel and the structural response of the ancient building constructed in (step two), the spatial correlation point pair of the utility tunnel and the ancient building corresponding to the point and the strongly correlated parameter pair corresponding to the abnormal parameter are extracted. At the same time, according to the risk transmission path determined by the model, the actual monitoring points on the path that have parameter correlation with the abnormal trigger monitoring point are selected.

[0151] Taking the abnormal trigger monitoring points as the core control targets, and combining the structural safety level, early warning level, risk transmission path, and related actual monitoring points of these points, a coordinated control plan for the safety of the utility tunnel and ancient buildings is formulated, specifically as follows:

[0152] The structural safety monitoring parameters that exceed the threshold in the abnormal trigger monitoring points are used as the basis for regulation, and the corresponding tunnel operation parameters or ancient building structural parameters are determined as the objects of regulation.

[0153] The control process is planned according to the logic of prioritizing the handling of abnormal trigger monitoring points and then preventing the risk from spreading to related monitoring points;

[0154] The structural safety level of the abnormal trigger monitoring point is used as the basic quantitative factor, and the early warning level is used as the correction quantitative factor. After assigning preset weight coefficients to the two types of quantitative factors, a weighted calculation is performed to obtain the quantitative value of the control intensity.

[0155] Several control intensity levels are set, and each control intensity level corresponds to a control intensity quantification value range. The control intensity quantification value corresponding to the abnormal trigger monitoring point is matched with all control intensity quantification value ranges, and the corresponding control intensity level is output.

[0156] The warning level, the matched control intensity level, the control object corresponding to the abnormal trigger monitoring point, and the control execution process of prioritizing the handling of abnormal trigger monitoring points and blocking the transmission of risks to related monitoring points are integrated into a collaborative control instruction and sent to the operation and maintenance management terminal.

[0157] The operation and maintenance control terminal conducts targeted operation and maintenance control of the utility tunnel's operating parameters and the structural parameters of ancient buildings based on collaborative control commands;

[0158] After the control is completed, structural safety monitoring parameters are collected at each actual monitoring point. The collected data is preprocessed by removing outliers and filling in missing values ​​to obtain valid monitoring data.

[0159] The preprocessed monitoring data is synchronously transmitted to the integrated digital twin basic model of the historical block corridor and ancient buildings. The model mapping parameters corresponding to the actual monitoring points and the corresponding structural safety monitoring parameters are updated according to the model mapping parameter correction process.

[0160] The preprocessed monitoring data is incorporated into the time-series monitoring dataset in timestamp order to complete the dataset update.

[0161] Based on the updated time-series monitoring dataset, the correlation degree of the pipe gallery-ancient building structure safety monitoring parameter pair is recalculated using the time-series cross-correlation analysis algorithm. The strongly correlated parameter pairs and risk transmission paths are updated to complete the iterative correction of the coupling relationship model between the pipe gallery operation status and the ancient building structure response.

[0162] By combining the updated monitoring data and the structural safety level of the actual monitoring points, the environmental correction coefficient is recalculated through the environmental impact dynamic correction model, and the hierarchical dynamic early warning thresholds for each actual monitoring point and each structural safety monitoring parameter are optimized.

[0163] By implementing a full-process cycle of monitoring data collection, hierarchical early warning judgment, collaborative control implementation, model parameter update, coupled model correction, and early warning threshold optimization, a closed loop of safety collaborative management and control is formed, realizing safety collaborative early warning and integrated management and control of utility tunnels and ancient buildings in historical blocks.

[0164] It should be noted that relying on the dynamic early warning threshold system to make early warning judgments can quickly identify abnormal locations by combining the actual status of monitoring parameters, respond to safety hazards in a timely manner, and reserve sufficient time for subsequent control operations.

[0165] Based on the coupling relationship model, the risk transmission path and related points are located. Combined with the structural safety level and early warning level, a coordinated control plan is formulated. This can focus on the root cause of the anomaly and carry out targeted treatment, while also taking into account risk prevention. This helps to reduce the impact of abnormal operation of the utility tunnel on the ancient building structure and meets the needs of coordinated protection of facilities in historical districts.

[0166] After the control is completed, the digital twin model, time series dataset, coupling relationship model and early warning threshold are updated and iteratively corrected in sync. This allows the system parameters and the model to continuously fit the actual situation on site, and gradually improves the adaptability of early warning and control.

[0167] Through a complete cycle of data collection, early warning judgment, control execution, and model iteration, a complete safety collaborative management and control closed loop is formed. The results of the initial modeling, analysis, and evaluation are translated into actual control actions, and the functions of the entire system are fully connected, providing continuous and coherent safety guarantees for the stable operation of the utility tunnel in historical districts and the protection of ancient building structures.

[0168] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A collaborative early warning system for the safety of utility tunnels and ancient buildings in historical districts based on digital twins, characterized in that: include: Twin model construction module: Obtain drawings and survey data of historical district utility tunnels and ancient buildings to construct an integrated 3D basic model; Virtual monitoring points are set up and actual monitoring points are selected and determined, and then linked and bound to the model. Structural safety monitoring data is collected, encoded, and mapped. Data fitting and deviation determination trigger model correction, forming an integrated digital twin basic model and time-series monitoring dataset. Coupling threshold modeling module: Filter spatial correlation point pairs between utility tunnel and ancient building and construct spatial correlation matrix, combine parameter pairs and calculate correlation degree to obtain strongly correlated parameter pairs; sort out risk transmission path and construct coupling relationship model; Calculate parameter deviation and location safety index to assess structural safety level, and construct and dynamically correct a graded dynamic early warning threshold system; The specific process of screening spatially related point pairs between utility tunnels and ancient buildings, constructing a spatial correlation matrix, combining parameter pairs, calculating the correlation degree, and obtaining strongly correlated parameter pairs is as follows: Based on the integrated digital twin basic model, the actual monitoring points of the utility tunnel and the actual monitoring points of the ancient buildings that are spatially adjacent or connected to it are extracted. Calculate the three-dimensional spatial distance between points, and combine the structural hierarchy to retain the point combinations at the same level or on the force transmission chain to determine the spatially related point pairs of the utility tunnel and ancient buildings. Using the associated point pair as rows and columns and the three-dimensional spatial distance as elements, a point spatial association matrix is ​​constructed; the structural safety monitoring parameters of the utility tunnel and the ancient building in the associated point pair are combined in pairs to form a utility tunnel-ancient building structural safety monitoring parameter pair. The time series of real-time fitted monitoring values ​​is retrieved, and the correlation degree of parameters is calculated using the time series cross-correlation analysis algorithm. Parameter pairs with a correlation degree greater than a preset threshold are marked as strongly correlated parameter pairs. The specific process of identifying risk transmission paths and constructing a coupling relationship model is as follows: Based on the spatial correlation points of the pipe gallery-ancient building corresponding to the strongly correlated parameter pairs, the time-series lag correlation analysis is used to determine the direction of influence transmission between parameters. Strongly correlated parameters with continuous transmission relationships are connected in series in the transmission order to form a one-way risk transmission path from changes in the operation parameters of the utility tunnel to the response of the structural parameters of the ancient building. Based on the spatial correlation matrix of points, the core of the parameter correlation is the strongly correlated parameter pairs, and the dynamic change logic is the risk transmission path. The three types of data are integrated according to the topological structure to construct a coupling relationship model between the operation status of the utility tunnel and the structural response of the ancient building. Safety collaborative management module: compares structural safety monitoring parameters with early warning thresholds to determine the early warning level and identify abnormal trigger points; Identify relevant locations and risk transmission paths, and formulate and implement targeted and coordinated control measures. After adjustment, the digital twin model and time series dataset are updated, and the coupled model and early warning threshold are iteratively corrected to form a closed loop of safe and collaborative management.

2. The historical district utility tunnel and ancient building safety collaborative early warning system based on digital twins as described in claim 1, characterized in that: The specific process of obtaining drawings and survey data of the historical district's utility tunnels and ancient buildings, and constructing an integrated 3D basic model, is as follows: Obtain historical district utility tunnel layout drawings and ancient building structure drawings, and simultaneously collect surveying data of the utility tunnels and ancient buildings; Using a BIM modeling platform, the dimensional deviations were corrected based on the utility tunnel drawings and on-site survey data. Three-dimensional model units of the main structure and auxiliary components of the utility tunnel were drawn, material parameters were entered and spliced ​​for verification, and a three-dimensional solid model of the utility tunnel was formed. Based on ancient architectural drawings and survey data, the shape and connection method of structural components are restored, three-dimensional model units are drawn, material parameters are entered and spliced ​​according to structural logic to form a three-dimensional solid model of the ancient building. Collect geospatial information of historical blocks and determine a unified spatial coordinate system. Import the two types of models into the coordinate system, align the coordinates with the pre-embedded fixed points as the reference, correct the overlapping areas of the models, complete the spatial fusion, and form an integrated three-dimensional basic model.

3. The historical district utility tunnel and ancient building safety collaborative early warning system based on digital twins as described in claim 2, characterized in that: The specific process of setting up virtual monitoring points, selecting and determining actual monitoring points, and associating and binding them with the model is as follows: Virtual monitoring points are evenly deployed throughout the entire area of ​​the utility tunnel and the entire area of ​​the ancient building. Based on the historical structural safety monitoring data of the main body corresponding to each virtual monitoring point, statistical feature values ​​are extracted as structural safety correlation parameters. Preset weight coefficients are assigned to each structural safety correlation parameter, and after normalization and dimensionless processing, the risk assessment value of the virtual point is obtained by weighted calculation. The risk assessment value is compared with the preset threshold. If the value meets the standard, it is marked as an actual monitoring point and the corresponding monitoring equipment is installed. The spatial coordinates of the actual monitoring point are collected and imported into the integrated three-dimensional basic model. The corresponding structural components are located through the coordinate comparison algorithm, and the association and binding between the actual monitoring point and the model components are completed by coordinate matching.

4. The historical district utility tunnel and ancient building safety collaborative early warning system based on digital twins as described in claim 3, characterized in that: The specific process of collecting structural safety monitoring data, encoding and mapping it, and triggering model correction through data fitting and deviation judgment to form an integrated digital twin basic model and time-series monitoring dataset is as follows: Structural safety monitoring parameters are collected in real time by monitoring equipment deployed at actual monitoring points, and the raw monitoring data is preprocessed. The preprocessed structural safety monitoring parameters are encoded according to preset rules and synchronously transmitted to the integrated three-dimensional basic model. The model update time step is preset. Within each step, the corresponding time series monitoring dataset is retrieved, the structural safety monitoring parameters are linearly fitted, and the real-time fitted monitoring values ​​and the fitting slope are extracted. The initial health status benchmark parameters and benchmark slope of the structural safety monitoring parameters are determined, the numerical deviation and trend deviation are calculated, and the comprehensive deviation value of the structural status is obtained after normalization. If the overall deviation value of the structural state meets the standard, the model mapping parameter correction process is triggered: the deviation value range is matched to obtain the overall deviation value correction coefficient, and the model mapping parameters of the corresponding points and parameters in the integrated three-dimensional basic model are updated according to the correction coefficient to form an integrated digital twin basic model; The data from each monitoring point are organized by timestamp to construct a time-series monitoring dataset that includes parameter type, real-time fitted monitoring value, timestamp, point code, and model correction record.

5. The historical district utility tunnel and ancient building safety collaborative early warning system based on digital twins as described in claim 4, characterized in that: The specific process of calculating parameter deviation and location safety index to assess structural safety level, and constructing and dynamically correcting a graded dynamic early warning threshold system is as follows: Retrieve the initial health status baseline parameters of each structure safety monitoring parameter at the actual monitoring points, and calculate the deviation of the parameter current status; Preset multiple deviation threshold ranges for each parameter and match the level coefficients. Match the deviation with the threshold ranges to obtain the corresponding level coefficients. By combining the level coefficients of each parameter with the preset weight coefficients, the overall safety index of the actual monitoring point is calculated. The safety index is then matched with the preset level range to determine the structural safety level of the point. Based on the time-series monitoring dataset and structural safety level, multiple initial warning thresholds are preset for each parameter. An environmental impact dynamic correction model is constructed to dynamically correct the initial thresholds, forming a three-level dynamic warning threshold for each parameter. Finally, a hierarchical dynamic safety warning threshold system covering the entire domain and all parameters is constructed.

6. The historical district utility tunnel and ancient building safety collaborative early warning system based on digital twins as described in claim 5, characterized in that: The specific process of comparing structural safety monitoring parameters with early warning thresholds to determine the early warning level and identify abnormal trigger points is as follows: Based on the full-domain, full-parameter hierarchical dynamic early warning threshold system, the structural safety monitoring parameters of each actual monitoring point are compared with the corresponding dynamic early warning thresholds of each level for that point and parameter, and the early warning level of the corresponding monitoring point is determined according to the threshold level exceeded by the parameter. When any structural safety monitoring parameter at an actual monitoring point exceeds any level of dynamic early warning threshold, that point is designated as an abnormal trigger monitoring point, and the corresponding early warning level is recorded simultaneously.

7. The historical district utility tunnel and ancient building safety collaborative early warning system based on digital twins as described in claim 6, characterized in that: The specific process of locating related points and risk transmission paths, and formulating and implementing targeted and coordinated regulation is as follows: Based on the abnormal trigger monitoring points, and based on the coupling relationship model between the operation status of the utility tunnel and the structural response of the ancient building, we extract the corresponding pairs of spatially related points of the utility tunnel and the ancient building, as well as the pairs of strongly related parameters corresponding to the abnormal parameters, and screen the associated actual monitoring points according to the risk transmission path. Taking the abnormal trigger monitoring points as the core control objects, and combining their structural safety level, early warning level, risk transmission path and related actual monitoring points, a safety collaborative control plan is formulated to determine the control objects and control processes. The quantitative value of the control intensity is calculated and matched with the corresponding control intensity level. The results are integrated to form a collaborative control instruction and sent to the operation and maintenance management terminal, which then executes the targeted operation and maintenance control.

8. The historical district utility tunnel and ancient building safety collaborative early warning system based on digital twins as described in claim 7, characterized in that: The specific process of updating the digital twin model and time-series dataset after regulation, iteratively correcting the coupled model and early warning threshold, and forming a closed loop for safe collaborative management and control is as follows: After the control is completed, the structural safety monitoring parameters of each actual monitoring point are collected and preprocessed. The preprocessed data is then synchronously transmitted to the integrated digital twin basic model, and the model mapping parameters of the corresponding points and parameters are updated according to the model mapping parameter correction process. The data is added to the time-series monitoring dataset in timestamp order to complete the update; the parameter correlation is recalculated based on the updated dataset, the strongly correlated parameter pairs and risk transmission paths are updated, and the coupling relationship model is iteratively corrected. By combining updated monitoring data with structural safety levels, the environmental correction factor is recalculated, and the graded dynamic early warning threshold is optimized. Through the cyclical execution of the entire process, a closed loop of safety collaborative management is formed, realizing the safety collaborative early warning and integrated management of utility tunnels and ancient buildings in historical districts.

Images