A full life cycle management system of a same-layer drainage system based on digital twinning

Abstract

The application relates to the technical field of intelligent drainage management, and discloses a full-life-cycle management system for a same-layer drainage system based on digital twinning, which comprises a pipeline three-dimensional modeling module, a joint traceability chain generation module, a digital twinning dynamic mapping module, a reverse traceability double-verification module and an operation and maintenance diagnosis report generation module, is used for cross-stage association binding of the same-layer drainage system to generate a space-time joint traceability chain; the three-dimensional information model and the operation state data are dynamically twinned and mapped to construct a digital twinning simulation model; when an abnormal signal is detected, a fault path is reversely traced along the space topology mapping data, double verification is carried out in combination with historical data trend analysis and real simulation, and a fault root cause diagnosis result is generated; a fault diagnosis report is generated based on the diagnosis result and the full-cycle data traceability chain and is pushed to an operation and maintenance terminal; and the application solves the problems of data fragmentation in each stage of the same-layer drainage system and low intelligent degree of hidden pipeline fault diagnosis.

Description

Technical Field

[0001] This invention relates to the field of intelligent drainage management technology, and in particular to a full lifecycle management system for a same-floor drainage system based on digital twins. Background Technology

[0002] In existing technologies, the full lifecycle management methods for in-floor drainage systems lack a unified spatial benchmark for linking and binding data across different stages. Data generated during the planning and design, construction and installation, and operation and maintenance phases of in-floor drainage systems are stored independently by the design institute, construction unit, and property management company, respectively. The data carriers and formats vary, making it difficult to establish effective correlations and mappings between data from different stages. When the system enters the operation and maintenance phase, the lack of a cross-stage data binding mechanism based on spatial topology means that key information such as pipe material specifications, installation process parameters, and concealed works records from the initial stage cannot be traced and correlated with fault data from the operation and maintenance phase. This makes it difficult for operation and maintenance personnel to obtain complete historical information about fault nodes when locating faults, resulting in low fault diagnosis efficiency and a lack of targeted repair solutions.

[0003] Existing technologies for intelligent fault diagnosis of in-floor drainage systems lack the ability to perform refined digital twin mapping of concealed pipe nodes. Pipes in in-floor drainage systems are buried in concealed spaces such as drop-down floors, false walls, and suspended ceilings. Traditional maintenance methods rely on regular manual inspections and user reports, representing passive management and failing to provide real-time monitoring of the internal operating status of these concealed pipes. Furthermore, current digital twin technology applications in drainage systems only perform threshold alarms based on data collected from monitoring nodes. They lack the ability to simulate and extrapolate the operating status of non-monitored pipe nodes without deployed sensors. Fault diagnosis relies solely on anomaly detection from a single data source, lacking a dual verification mechanism combining historical data trend analysis and forward simulation based on digital twins. This results in insufficient accuracy and a high false alarm rate in root cause diagnosis. Therefore, there is an urgent need to develop an intelligent fault diagnosis method that combines flow pattern extrapolation and dual verification to address the problems of unknown operating status of concealed pipe nodes and inaccurate root cause location, thereby improving the intelligence level of fault diagnosis in in-floor drainage systems. Summary of the Invention

[0004] To achieve the above objectives, this invention provides a full lifecycle management system for a same-floor drainage system based on digital twins. The system comprises a pipeline 3D modeling module, a joint traceability chain generation module, a digital twin dynamic mapping module, a reverse traceability dual verification module, and an operation and maintenance diagnostic report generation module, wherein: The pipeline 3D modeling module is used to construct a 3D information model based on the pipeline topology of a same-floor drainage system. The joint traceability chain generation module is used to perform cross-stage association binding on the same-floor drainage system based on the spatial topology mapping data in the three-dimensional information model, and generate a spatiotemporal joint traceability chain for each hidden pipe node in the same-floor drainage system. The digital twin dynamic mapping module is used to dynamically map the three-dimensional information model with the operating status data of each hidden pipe node to construct a digital twin simulation model of the same-floor drainage system. The reverse tracing dual verification module, when the digital twin simulation model detects an abnormal signal, traces the fault path in reverse based on the spatial topology mapping data, and performs dual verification by combining the historical data change trend in the spatiotemporal joint tracing chain with the forward simulation results of the digital twin simulation model, generating a fault root cause diagnosis result. The operation and maintenance diagnosis report generation module is used to generate a fault diagnosis report for the same-floor drainage system based on the fault root cause diagnosis results and the full-cycle data traceability chain of the corresponding hidden pipe nodes, and push the fault diagnosis report to the operation and maintenance terminal of the same-floor drainage system.

[0005] In a preferred embodiment, the pipeline 3D modeling module, when constructing a 3D information model based on the pipeline topology of a same-floor drainage system, is specifically used for: Based on the topological structure type of the same-floor drainage system, identify the hidden spatial location type of each hidden pipe node, and establish an inclusion mapping relationship between each hidden pipe node and the hidden spatial location type; Based on the aforementioned mapping relationship, hierarchical spatial encoding is assigned to each hidden pipeline node; The hierarchical spatial coding and the pipeline topology of each hidden pipeline node are correlated and fused to generate spatial topology mapping data and construct a three-dimensional information model.

[0006] In a preferred embodiment, when the joint tracing chain generation module performs cross-stage association binding of the same-floor drainage system using the spatial topology mapping data in the three-dimensional information model as a spatial reference to generate a spatiotemporal joint tracing chain for each hidden pipe node in the same-floor drainage system, it is specifically used for: Using the spatial topology mapping data as the association anchor point, the multi-dimensional heterogeneous data of the same-floor drainage system is mapped and associated. The multi-dimensional heterogeneous data includes data from the planning and design stage, data from the construction and installation stage, and data from the operation and maintenance management stage. Establish a mapping relationship between the planning and design stage data and the spatial location of each concealed pipeline node to obtain the first binding mapping relationship; The construction and installation stage data and the spatial location are matched and associated to obtain a second binding mapping relationship; Establish a third binding mapping relationship between the historical fault locations in the operation and maintenance management phase data and the hierarchical spatial coding; The first binding mapping relationship, the second binding mapping relationship, and the third binding mapping relationship are merged and sorted in chronological order to form a spatiotemporal joint tracing chain for each hidden pipeline node.

[0007] In a preferred embodiment, when the digital twin dynamic mapping module performs dynamic twin mapping between the three-dimensional information model and the operational status data of each hidden pipe node to construct a digital twin simulation model of the same-floor drainage system, it is specifically used for: Based on the connectivity of concealed pipe segments in the spatial topology mapping data, starting from the monitoring nodes of each concealed pipe node, non-monitoring nodes are identified along the pipe topology to generate a set of non-monitoring nodes. Based on the preset pipe segment flow pattern deduction formula, flow pattern deduction is performed on the set of non-monitoring nodes to obtain the simulated operating status data of the non-monitoring nodes; The operational status data of each concealed pipe node and the simulated operational status data are input into the corresponding concealed pipe node in the three-dimensional information model to drive the status parameters of each concealed pipe node to be updated synchronously in real time. Based on the updated status parameters, a digital twin simulation model of the same-floor drainage system is constructed.

[0008] In a preferred embodiment, the preset flow regime deduction formula for the pipe segment is: ; in, This serves as an index identifier for adjacent monitoring nodes. This serves as the index identifier for non-monitored nodes. For the first Simulated operational status data of non-monitoring nodes, For the first Traffic data from adjacent monitoring nodes For the first Manning roughness coefficient at each non-monitoring node For the first Manning roughness coefficient at adjacent monitoring nodes For the first The cross-sectional area of ​​water flow at each non-monitoring node For the first The cross-sectional area of ​​water flow at each adjacent monitoring node For the first Hydraulic radius at each non-monitoring node For the first Hydraulic radius at adjacent monitoring nodes For the first Pipeline bottom slope at non-monitoring nodes For the first The pipeline bottom slope at each adjacent monitoring node.

[0009] In a preferred embodiment, when the reverse tracing dual verification module executes the following steps to generate a fault root cause diagnosis result: it traces the fault path backward based on the spatial topology mapping data when the digital twin simulation model detects an abnormal signal, and performs dual verification by combining the historical data change trends in the spatiotemporal joint tracing chain with the forward simulation results of the digital twin simulation model: When the digital twin simulation model detects an abnormal signal, it traces back to the upstream pipeline node based on the abnormal behavior node in the hidden pipeline node and the connection relationship of the hidden pipeline segment in the spatial topology mapping data, thus generating a fault propagation path. Based on the spatiotemporal joint tracing chain, the temporal change trend of historical operating status data in each hidden pipeline node is analyzed along the fault propagation path to generate historical trend analysis results. In the digital twin simulation model, different fault assumptions are applied to each hidden pipeline node on the fault propagation path for forward simulation and deduction, generating forward simulation results under each fault assumption condition; The historical trend analysis results are compared and matched with the forward simulation results to filter out the fault assumptions that are consistent between the two, and generate the root cause diagnosis results of the fault.

[0010] In a preferred embodiment, when the reverse tracing dual verification module executes the analysis of the time variation trend of historical operating status data in each hidden pipeline node along the fault propagation path based on the spatiotemporal joint tracing chain and generates historical trend analysis results, it is specifically used for: From the spatiotemporal joint tracing chain, the historical flow change data and historical pipe wall pressure data on the fault propagation path are subjected to trend fitting processing to identify whether there is a gradual deterioration trend or a sudden abnormal jump in the operating status data of each hidden pipe node, and generate trend feature markers for each hidden pipe node. Based on the trend feature markers, the abnormal start time of each hidden pipeline node is determined, the hidden pipeline node with the earliest abnormal start time is marked as a suspected root cause node, and the historical trend analysis results are generated.

[0011] In a preferred embodiment, when the reverse tracing dual verification module performs forward simulation and deduction by applying different fault assumptions to each hidden pipeline node along the fault propagation path in the digital twin simulation model, and generates forward simulation results under each fault assumption condition, it is specifically used for: Based on the concealed spatial location type of each concealed pipe node in the spatial topology mapping data, a set of typical fault types for each node is determined, including pipe siltation, water seal failure, and concealed leakage. For each hidden pipe node on the fault propagation path, apply each fault assumption condition from the typical fault type set in sequence, and adjust the physical parameters of the corresponding hidden pipe node in the digital twin simulation model. The physical parameters include the effective flow area of ​​the pipe, the water seal depth, and the permeability coefficient of the drop plate layer. The digital twin simulation model is driven to perform forward simulation and deduction along the fault propagation path from the hidden pipeline node where the fault assumption is applied to the downstream, so as to obtain the simulated operating status data of each downstream node. The simulated operating status data of each downstream node is compared with the actual operating status data collected in the digital twin simulation model to calculate a comprehensive deviation score. The fault assumption condition with the smallest comprehensive deviation score is selected to generate a positive simulation result.

[0012] In a preferred embodiment, the formula for calculating the comprehensive deviation score is: ; in, For the first Comprehensive deviation score under various failure assumptions. For the first fault propagation path The index identifier of each downstream node. This serves as an index identifier for the fault assumption conditions. This represents the total number of downstream nodes along the fault propagation path. For the traversal index of all downstream nodes, For the first The topological distance between each downstream node and the root cause node of the fault in the concealed pipeline node. In the first Under the first type of failure assumption, the first Simulated operating status data of each downstream node For the first The operational status data of each downstream node. For the first The topological distance between each downstream node and the root cause node of the fault.

[0013] In a preferred embodiment, when the maintenance diagnosis report generation module generates a fault diagnosis report for the same-floor drainage system based on the root cause diagnosis results and the corresponding concealed pipe node's full-cycle data tracing chain, and pushes the fault diagnosis report to the maintenance terminal of the same-floor drainage system, it is specifically used for: The concealed pipe routing information and engineering background data in the root cause diagnosis results are integrated to generate a fault diagnosis report for the same-floor drainage system. The fault diagnosis report is pushed to the operation and maintenance terminal of the same-floor drainage system, and the corresponding maintenance entrance location and maintenance path guidance are marked in the fault diagnosis report according to the concealed space location type marked in the concealed pipe routing information.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention achieves efficient integration and traceability of the entire lifecycle management information of the same-floor drainage system by constructing a cross-stage data association and binding mechanism based on hierarchical spatial coding. Using hierarchical spatial coding as the association anchor point, design parameters from the planning and design stage, construction records from the construction and installation stage, and operation and maintenance history from the operation and maintenance management stage are uniformly bound across stages, breaking down data barriers between various participants and solving the problem of information silos caused by data fragmentation at different stages. By establishing first, second, and third binding mapping relationships, each concealed pipeline node possesses a complete data traceability chain from design to operation and maintenance. Operation and maintenance personnel can directly obtain the pipe material, pipe diameter, installation process, and historical maintenance records of a faulty node through its spatial coding, without having to sift through scattered data from different stages, significantly improving the efficiency of information acquisition for fault diagnosis. The association and binding relationship established based on spatial topology mapping data has spatial uniqueness. Even if the pipeline is buried in concealed spaces such as within a drop slab layer or a false wall, the corresponding historical data can still be accurately located through spatial coding, effectively avoiding the loss of concealed engineering information during long-term operation and maintenance.

[0015] 2. This invention achieves accurate root cause location of hidden pipe nodes in the same-floor drainage system by combining flow pattern deduction and reverse tracing for dual verification of intelligent fault diagnosis method. Based on the flow pattern extrapolation formula for pipe segments, the operational status of non-monitored pipeline nodes without deployed sensors is simulated and extrapolated. This enables the digital twin simulation model to cover all hidden pipeline nodes, solving the problem of unknown operational status of hidden pipelines and eliminating the limitation of relying solely on monitoring node data for judgment in traditional operation and maintenance. By tracing the fault propagation path in reverse and combining a dual verification mechanism of historical data trend analysis and forward simulation of digital twin simulation, the historical degradation trend in the time dimension is compared and matched with the simulation extrapolation results in the spatial dimension. This avoids false alarms and missed alarms caused by abnormal judgments from a single data source, improving the accuracy of fault root cause diagnosis. Based on the comprehensive deviation scoring calculation method of topological distance weighting, the diagnostic results focus more on the fitting degree of downstream nodes closer to the fault root cause node, enhancing the directionality of root cause location. This provides operation and maintenance personnel with a complete diagnostic report that includes accurate fault node location, hidden pipeline route reconstruction, and maintenance path guidance, significantly reducing the destructive cost and maintenance response time of hidden pipeline maintenance. Attached Figure Description

[0016] Figure 1 A system architecture diagram of a digital twin-based full lifecycle management system for a floor-to-floor drainage system is provided as an embodiment of the present invention. The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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 belong to some, but not all, embodiments of the present invention. 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.

[0018] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “said” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0019] Depending on the context, the word "if" or "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0020] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0021] In practice, the server-side equipment deployed in a digital twin-based same-level drainage system lifecycle management system may consist of one or more devices. This digital twin-based same-level drainage system lifecycle management system can be implemented as: a business instance, a virtual machine, and hardware devices. For example, this digital twin-based same-level drainage system lifecycle management system can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, this digital twin-based same-level drainage system lifecycle management system can be understood as software deployed on a cloud node, used to provide each user terminal with a digital twin-based same-level drainage system lifecycle management system. Alternatively, this digital twin-based same-level drainage system lifecycle management system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. This virtual machine contains application software for managing each user terminal. Alternatively, this digital twin-based same-level drainage system lifecycle management system can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide each user terminal with a digital twin-based same-level drainage system lifecycle management system.

[0022] In terms of implementation, a digital twin-based system for the entire lifecycle management of a same-floor drainage system and its user terminal are mutually compatible. Specifically, if the system is implemented as an application installed on a cloud service platform, the user terminal acts as a client establishing a communication connection with that application; or if the system is implemented as a website, the user terminal acts as a webpage; or if the system is implemented as a cloud service platform, the user terminal acts as a mini-program within an instant messaging application.

[0023] like Figure 1 The diagram shown is a system architecture diagram of a digital twin-based full life cycle management system for a floor drainage system provided by an embodiment of the present invention.

[0024] The digital twin-based lifecycle management system 100 for a same-floor drainage system described in this invention can be hosted on a cloud server. In terms of implementation, it can function as one or more service devices, or as an application installed in the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed into a website. Depending on the functions implemented, the digital twin-based lifecycle management system 100 may include a pipeline 3D modeling module 101, a joint traceability chain generation module 102, a digital twin dynamic mapping module 103, a reverse traceability dual verification module 104, and an operation and maintenance diagnostic report generation module 105. The modules described in this invention can also be called units, referring to a series of computer program segments that can be executed by an electronic device's processor and perform a fixed function, stored in the electronic device's memory.

[0025] In this embodiment of the invention, in a digital twin-based lifecycle management system for a same-floor drainage system, each of the above-mentioned modules can be implemented independently and can call other modules. Here, "calling" can be understood as a module connecting to multiple modules of another type and providing corresponding services to those connected modules. In this embodiment of the invention, the applicability of the digital twin-based lifecycle management system architecture can be adjusted by adding modules and directly calling them without modifying the program code, achieving cluster-based horizontal expansion. This allows for quick and flexible expansion of the digital twin-based lifecycle management system. In practical applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in a cloud server.

[0026] The following describes, with reference to specific embodiments, each component and specific workflow of a digital twin-based full lifecycle management system for in-floor drainage systems: The pipeline 3D modeling module 101 is used to construct a 3D information model based on the pipeline topology of the same-floor drainage system. In this embodiment of the invention, when the pipeline 3D modeling module executes the pipeline topology structure based on the same-floor drainage system to construct a 3D information model, it is specifically used for: Based on the topological structure type of the same-floor drainage system, identify the hidden spatial location type of each hidden pipe node, and establish an inclusion mapping relationship between each hidden pipe node and the hidden spatial location type; Based on the aforementioned mapping relationship, hierarchical spatial encoding is assigned to each hidden pipeline node; The hierarchical spatial coding and the pipeline topology of each hidden pipeline node are correlated and fused to generate spatial topology mapping data and construct a three-dimensional information model.

[0027] The connection relationships and spatial location information between each concealed pipe node are obtained from the pipe topology of the same-floor drainage system. The pipe topology describes the upstream and downstream connectivity between each concealed pipe node and their relative positional relationship in the building space.

[0028] Based on the topological structure of the same-floor drainage system, the building concealed space where each concealed pipe node is located is classified and identified. The concealed space location types include three types: the area inside the drop slab layer, the area inside the false wall, and the area inside the ceiling. The area inside the drop slab layer is the pipe laying space formed by the drop slab of the bathroom floor structure, the area inside the false wall is the pipe laying space formed inside the false wall of the bathroom, and the area inside the ceiling is the pipe laying space formed inside the ceiling of the bathroom.

[0029] After identification, an inclusion mapping relationship is established between each hidden pipe node and the hidden spatial location type. This inclusion mapping relationship records the hidden spatial location type to which each hidden pipe node belongs, providing a spatial location classification basis for assigning spatial codes.

[0030] Based on the concealed spatial location type of each concealed pipe node in the mapping relationship, each concealed pipe node is classified and grouped according to its concealed spatial location type: those belonging to the area within the drop floor are grouped into one group, those belonging to the area within the false wall are grouped into another group, and those belonging to the area within the suspended ceiling are grouped into yet another group.

[0031] Within each group, based on the connection order and floor affiliation of each concealed pipe node in the pipe topology, a hierarchical spatial code is assigned to each concealed pipe node, which is composed of a region code, a floor code, a concealed space location type code, and a horizontal sequence number code. The region code identifies the building area to which the concealed pipe node belongs, the floor code identifies the floor where the concealed pipe node is located, the concealed space location type code identifies whether the concealed pipe node belongs to the area within the drop floor, the area within the false wall, or the area within the suspended ceiling, and the horizontal sequence number code identifies the sequence number of the concealed pipe node within the same concealed space location type. This hierarchical spatial code is spatially unique, and each concealed pipe node corresponds to a unique hierarchical spatial code.

[0032] The hierarchical attribution information contained in the hierarchical spatial coding is matched with the node connection relationship contained in the pipeline topology of each hidden pipeline node, so that each hidden pipeline node has a hierarchical attribution identifier of spatial location while retaining its upstream and downstream connectivity.

[0033] The hierarchical spatial codes that have been matched and matched are integrated with the pipeline topology to establish a bidirectional mapping between the hierarchical spatial codes of each hidden pipeline node and its upstream and downstream connection relationships in the pipeline topology, generating spatial topology mapping data. This spatial topology mapping data includes both the spatial hierarchical affiliation relationship of each hidden pipeline node and the pipeline connectivity topology relationship.

[0034] Based on the spatial location information and pipeline connection relationships of each hidden pipeline node in the spatial topology mapping data, a three-dimensional geometric model of each hidden pipeline node is constructed in three-dimensional space, and the pipeline connection relationships between each hidden pipeline node are established, generating a three-dimensional information model containing the spatial location, pipeline direction, and connection relationships of each hidden pipeline node.

[0035] The beneficial effects are as follows: The above steps identify the concealed spatial location type of each concealed pipe node based on the topological structure type of the same-floor drainage system and establish an inclusion mapping relationship, so that each concealed pipe node has a clear spatial location classification identifier, effectively solving the problem of unclear location information of concealed pipe nodes in concealed spaces such as dropped floors, false walls, and suspended ceilings. Based on the inclusion mapping relationship, each concealed pipe node is assigned a hierarchical spatial code composed of area code, floor code, concealed spatial location type code, and horizontal sequence number code, so that each concealed pipe node has a spatially unique code identifier, providing a unified spatial association anchor point for cross-stage data association and binding, effectively solving the problem that data at different stages cannot be associated due to the lack of a unified spatial identifier. The hierarchical spatial code is associated and fused with the pipe topology to generate spatial topology mapping data and construct a three-dimensional information model, so that the three-dimensional information model has both spatial hierarchy information and pipe connectivity topology information, providing accurate spatial topology basic data for subsequent digital twin dynamic mapping, reverse fault tracing, and maintenance path planning.

[0036] The joint traceability chain generation module 102 is used to perform cross-stage association binding on the same-floor drainage system using the spatial topology mapping data in the three-dimensional information model as a spatial reference, and generate a spatiotemporal joint traceability chain for each hidden pipe node in the same-floor drainage system. In this embodiment of the invention, when the joint traceability chain generation module performs cross-stage association binding of the same-floor drainage system using the spatial topology mapping data in the three-dimensional information model as a spatial reference to generate a spatiotemporal joint traceability chain for each hidden pipe node in the same-floor drainage system, it is specifically used for: Using the spatial topology mapping data as the association anchor point, the multi-dimensional heterogeneous data of the same-floor drainage system is mapped and associated. The multi-dimensional heterogeneous data includes data from the planning and design stage, data from the construction and installation stage, and data from the operation and maintenance management stage. Establish a mapping relationship between the planning and design stage data and the spatial location of each concealed pipeline node to obtain the first binding mapping relationship; The construction and installation stage data and the spatial location are matched and associated to obtain a second binding mapping relationship; Establish a third binding mapping relationship between the historical fault locations in the operation and maintenance management phase data and the hierarchical spatial coding; The first binding mapping relationship, the second binding mapping relationship, and the third binding mapping relationship are merged and sorted in chronological order to form a spatiotemporal joint tracing chain for each hidden pipeline node.

[0037] Data from the planning and design phase, construction and installation phase, and operation and maintenance phase are collected from the same-floor drainage system. The planning and design phase data includes the pipe layout scheme and pipe diameter specifications in the design drawings. The construction and installation phase data includes the installation location description and installation process parameters recorded during construction. The operation and maintenance phase data includes fault records and maintenance history generated during operation and maintenance.

[0038] The diverse and heterogeneous data are classified and grouped according to the stage of the data source, and the hierarchical spatial coding in the spatial topology mapping data is used as a unified spatial association anchor point to provide a unified spatial identification benchmark for the one-to-one mapping association between data and spatial location in subsequent stages.

[0039] The pipeline numbers and pipeline layout information marked in the design drawings are extracted from the data of the planning and design stage. Then, the pipeline numbers are compared and matched one by one with the hierarchical spatial codes. The pipeline numbers and pipe diameter specifications in the design stage are associated with the spatial locations of the corresponding hidden pipeline nodes, and the first binding mapping relationship between the data of the planning and design stage and the spatial locations is established, so that each hidden pipeline node can be traced back to its original design parameters in the design stage.

[0040] The installation location description and installation process parameters are extracted from the construction records of the construction and installation stage data. Then, the installation location description is semantically matched with the concealed space location type and floor affiliation identified by the hierarchical spatial code. The installation process parameters and actual pipe diameter of the installation stage are associated with the spatial location of the corresponding concealed pipe node, and a second binding mapping relationship between the construction and installation stage data and the spatial location is established, so that each concealed pipe node can be traced back to its installation record information in the construction stage.

[0041] The fault location description and fault type information are extracted from the historical fault records in the operation and maintenance management phase data. Then, the fault location description is matched with the hierarchical spatial code to associate the fault records and maintenance history of the operation and maintenance phase with the spatial location of the corresponding hidden pipeline node. A third binding mapping relationship between the operation and maintenance management phase data and spatial location is established, so that each hidden pipeline node can trace its historical fault data in the operation and maintenance phase.

[0042] Using the hierarchical spatial encoding as the common association key, the data belonging to the same concealed pipeline node in the first binding mapping relationship, the second binding mapping relationship, and the third binding mapping relationship are merged. Then, the merged data is arranged chronologically according to the planning and design stage, the construction and installation stage, and the operation and maintenance management stage, to generate a spatiotemporal joint traceability chain for each concealed pipeline node from design to operation and maintenance. This spatiotemporal joint traceability chain records the complete data information of each concealed pipeline node at each stage of its entire life cycle.

[0043] The beneficial effects are as follows: The above steps use the hierarchical spatial coding in the spatial topology mapping data as a unified spatial association anchor point to map the spatial location of the diverse and heterogeneous data generated in the planning and design stage, construction and installation stage, and operation and maintenance management stage one by one. This effectively breaks down the information barriers between data in each stage, enabling each hidden pipeline node to have complete data traceability capabilities from design to operation and maintenance. Operation and maintenance personnel can directly obtain the full life cycle historical data of the hidden pipeline node through the spatial coding of the hidden pipeline node, without having to search repeatedly between different participants and different data carriers, which significantly improves the efficiency of information acquisition when troubleshooting hidden pipeline faults.

[0044] The digital twin dynamic mapping module 103 is used to dynamically map the three-dimensional information model with the operating status data in each hidden pipe node to construct a digital twin simulation model of the same-floor drainage system. In this embodiment of the invention, when the digital twin dynamic mapping module performs dynamic twin mapping between the three-dimensional information model and the operating status data of each hidden pipe node to construct a digital twin simulation model of the same-floor drainage system, it is specifically used for: Based on the connectivity of concealed pipe segments in the spatial topology mapping data, starting from the monitoring nodes of each concealed pipe node, non-monitoring nodes are identified along the pipe topology to generate a set of non-monitoring nodes. Based on the preset pipe segment flow pattern deduction formula, flow pattern deduction is performed on the set of non-monitoring nodes to obtain the simulated operating status data of the non-monitoring nodes; The operational status data of each concealed pipe node and the simulated operational status data are input into the corresponding concealed pipe node in the three-dimensional information model to drive the status parameters of each concealed pipe node to be updated synchronously in real time. Based on the updated status parameters, a digital twin simulation model of the same-floor drainage system is constructed.

[0045] The preset flow regime deduction formula for the pipe section is as follows: ; in, This serves as an index identifier for adjacent monitoring nodes. This serves as the index identifier for non-monitored nodes. For the first Simulated operational status data of non-monitoring nodes, For the first Traffic data from adjacent monitoring nodes For the first Manning roughness coefficient at each non-monitoring node For the first Manning roughness coefficient at adjacent monitoring nodes For the first The cross-sectional area of ​​water flow at each non-monitoring node For the first The cross-sectional area of ​​water flow at each adjacent monitoring node For the first Hydraulic radius at each non-monitoring node For the first Hydraulic radius at adjacent monitoring nodes For the first Pipeline bottom slope at non-monitoring nodes For the first The pipeline bottom slope at each adjacent monitoring node.

[0046] When identifying non-monitoring nodes and generating a set of non-monitoring nodes based on the connectivity relationships of concealed pipe segments in the spatial topology mapping data, starting from the monitoring nodes of each concealed pipe node and traversing the pipeline topology, the connectivity relationships of concealed pipe segments between each concealed pipe node are first obtained from the spatial topology mapping data. These connectivity relationships describe the upstream and downstream connection paths between each concealed pipe node via pipes. Then, monitoring nodes with deployed flow sensors and depth sensors are selected from each concealed pipe node. Starting from these monitoring nodes, the process extends and traverses the upstream and downstream connection paths of the pipeline topology level by level to identify concealed pipe nodes without any deployed sensors. These sensorless concealed pipe nodes are then grouped to generate a set of non-monitoring nodes. This set of non-monitoring nodes records all concealed pipe nodes whose operational status data needs to be obtained through simulation.

[0047] One non-monitoring node is selected from the set of non-monitoring nodes. The pipe material parameters and pipe elevation information between the non-monitoring node and its adjacent monitoring nodes are obtained from the spatial topology mapping data. Then, the Manning roughness coefficient at the non-monitoring node and the Manning roughness coefficient at the adjacent monitoring node are determined based on the pipe material parameters. The pipe bottom slope at the non-monitoring node and the pipe bottom slope at the adjacent monitoring node are calculated based on the pipe elevation information.

[0048] Extract flow rate and pipe water depth data for the monitoring node from the operational status data of adjacent monitoring nodes. Calculate the cross-sectional area and hydraulic radius of the adjacent monitoring node based on the pipe diameter and water depth. Estimate the cross-sectional area and hydraulic radius of the non-monitoring node based on the pipe diameter and water depth of the adjacent monitoring node.

[0049] The acquired data is substituted into a preset pipe segment flow pattern deduction formula for calculation, and the simulated flow data of the non-monitoring node is derived. This simulated flow data is then used as the simulated operating status data of the non-monitoring node. The above deduction process is repeated for each non-monitoring node in the set of non-monitoring nodes until all non-monitoring nodes have obtained corresponding simulated operating status data.

[0050] The actual operational status data collected by the monitoring nodes and the simulated operational status data obtained by flow simulation from non-monitoring nodes are input into the corresponding hidden pipe nodes in the three-dimensional information model according to the hierarchical spatial coding corresponding to each hidden pipe node.

[0051] After receiving the corresponding operating status data, each hidden pipe node in the three-dimensional information model drives the real-time synchronous update of status parameters such as the fluid velocity inside the pipe, the pressure state of the pipe wall, and the water content of the drop layer.

[0052] Based on the updated state parameters, the visualization state of each hidden pipe node in the three-dimensional information model is rendered in real time, so that the state of each hidden pipe node in the digital twin simulation model is consistent with the actual physical system, and a digital twin simulation model of the same-floor drainage system covering all hidden pipe nodes is constructed.

[0053] The beneficial effects are as follows: The above steps, based on a preset pipe segment flow pattern derivation formula, perform flow pattern derivation on the set of non-monitored nodes to obtain simulated operating status data. This formula is derived from the Manning formula and is applicable to the hydraulic characteristics of gravity-driven unpressurized flow in the same-floor drainage system. By comprehensively considering parameters such as the Manning roughness coefficient, cross-sectional area, hydraulic radius, and pipe bottom slope, reliable operating status estimates can be obtained for hidden pipe nodes without deployed sensors, filling the blind spot in the monitoring of hidden pipe operating status and providing data support for the integrity of the digital twin simulation model. The operating status data and simulated operating status data are uniformly input into the three-dimensional information model to drive the real-time synchronous update of status parameters and construct the digital twin simulation model. This allows the digital twin simulation model to cover all hidden pipe nodes, enabling maintenance personnel to grasp the overall operating status of the hidden pipe system in real time through the digital twin simulation model, providing a complete data foundation for subsequent anomaly detection and fault diagnosis.

[0054] The reverse tracing dual verification module 104, when the digital twin simulation model detects an abnormal signal, traces the fault path in reverse based on the spatial topology mapping data, and performs dual verification by combining the historical data change trend in the spatiotemporal joint tracing chain with the forward simulation results of the digital twin simulation model, and generates a fault root cause diagnosis result. In this embodiment of the invention, when the digital twin simulation model detects an abnormal signal, the reverse tracing dual verification module reversely traces the fault path based on the spatial topology mapping data and performs dual verification by combining the historical data change trend in the spatiotemporal joint tracing chain with the forward simulation results of the digital twin simulation model to generate a fault root cause diagnosis result, specifically used for: When the digital twin simulation model detects an abnormal signal, it traces back to the upstream pipeline node based on the abnormal behavior node in the hidden pipeline node and the connection relationship of the hidden pipeline segment in the spatial topology mapping data, thus generating a fault propagation path. Based on the spatiotemporal joint tracing chain, the temporal change trend of historical operating status data in each hidden pipeline node is analyzed along the fault propagation path to generate historical trend analysis results. In the digital twin simulation model, different fault assumptions are applied to each hidden pipeline node on the fault propagation path for forward simulation and deduction, generating forward simulation results under each fault assumption condition; The historical trend analysis results are compared and matched with the forward simulation results to filter out the fault assumptions that are consistent between the two, and generate the root cause diagnosis results of the fault.

[0055] The reverse tracing dual verification module, when executing the spatiotemporal joint tracing chain based on the fault propagation path, analyzes the time change trend of historical operating status data in each hidden pipeline node and generates historical trend analysis results, is specifically used for: From the spatiotemporal joint tracing chain, the historical flow change data and historical pipe wall pressure data on the fault propagation path are subjected to trend fitting processing to identify whether there is a gradual deterioration trend or a sudden abnormal jump in the operating status data of each hidden pipe node, and generate trend feature markers for each hidden pipe node. Based on the trend feature markers, the abnormal start time of each hidden pipeline node is determined, the hidden pipeline node with the earliest abnormal start time is marked as a suspected root cause node, and the historical trend analysis results are generated.

[0056] When the reverse tracing dual verification module executes forward simulation in the digital twin simulation model, applying different fault assumptions to each hidden pipeline node along the fault propagation path and generating forward simulation results under each fault assumption, it is specifically used for: Based on the concealed spatial location type of each concealed pipe node in the spatial topology mapping data, a set of typical fault types for each node is determined, including pipe siltation, water seal failure, and concealed leakage. For each hidden pipe node on the fault propagation path, apply each fault assumption condition from the typical fault type set in sequence, and adjust the physical parameters of the corresponding hidden pipe node in the digital twin simulation model. The physical parameters include the effective flow area of ​​the pipe, the water seal depth, and the permeability coefficient of the drop plate layer. The digital twin simulation model is driven to perform forward simulation and deduction along the fault propagation path from the hidden pipeline node where the fault assumption is applied to the downstream, so as to obtain the simulated operating status data of each downstream node. The simulated operating status data of each downstream node is compared with the actual operating status data collected in the digital twin simulation model to calculate a comprehensive deviation score. The fault assumption condition with the smallest comprehensive deviation score is selected to generate a positive simulation result.

[0057] The formula for calculating the comprehensive deviation score is as follows: ; in, For the first Comprehensive deviation score under various failure assumptions. For the first fault propagation path The index identifier of each downstream node. This serves as an index identifier for the fault assumption conditions. This represents the total number of downstream nodes along the fault propagation path. For the traversal index of all downstream nodes, For the first The topological distance between each downstream node and the root cause node of the fault in the concealed pipeline node. In the first Under the first type of failure assumption, the first Simulated operating status data of each downstream node For the first The operational status data of each downstream node. For the first The topological distance between each downstream node and the root cause node of the fault.

[0058] Hidden pipe nodes that detect abnormal signals are obtained from the digital twin simulation model and identified as anomalous nodes. Then, the connectivity of the hidden pipe segments is obtained from the spatial topology mapping data. Starting from the anomalous node, the upstream connectivity of the hidden pipe segments is traced step by step to find upstream pipe nodes connected to the anomalous node via pipes. Each upstream pipe node is then used as a new starting point to continue tracing upstream until the source node of the pipe topology is reached. All hidden pipe nodes traversed from the anomalous node to the source node are arranged in tracing order to generate a fault propagation path. This path records the possible propagation direction of the anomalous signal and the sequence of hidden pipe nodes it passes through.

[0059] Historical flow rate change data and historical pipe wall pressure data of each hidden pipeline node on the fault propagation path within a preset time window are extracted from the spatiotemporal joint tracing chain. Then, trend fitting processing is performed on the historical flow rate change data and historical pipe wall pressure data. By calculating the slope and fluctuation amplitude of the operating status data of each hidden pipeline node in the time series, it is identified whether there is a gradual deterioration trend such as gradual flow rate decline and continuous pressure increase, or whether there is a sudden abnormal jump such as sudden flow rate drop and sudden pressure increase. The identified trend type is marked as the trend feature label of the hidden pipeline node.

[0060] Based on the degradation trend type and abnormal jump time of each hidden pipeline node in the trend feature markers, the time point when the operating status data of each hidden pipeline node first deviated from the normal range is traced back, and this time point is determined as the abnormal start time of that hidden pipeline node. Then, the abnormal start times of all hidden pipeline nodes on the fault propagation path are compared, and the hidden pipeline node with the earliest abnormal start time is marked as the suspected root cause node. This suspected root cause node represents the hidden pipeline node that first exhibited operational abnormality in the time dimension. Finally, the trend feature markers, abnormal start times, and suspected root cause node information of each hidden pipeline node are summarized to generate historical trend analysis results.

[0061] The concealed spatial location type of each concealed pipe node on the fault propagation path is obtained from the spatial topology mapping data. Then, based on the concealed spatial location type of each concealed pipe node, the typical fault types that may occur for that concealed pipe node are determined. The typical fault types of concealed pipe nodes located in the area within the drop floor include pipe siltation and concealed leakage; the typical fault types of concealed pipe nodes located in the area within the false wall include pipe siltation and water seal failure; and the typical fault type of concealed pipe nodes located in the area within the suspended ceiling includes pipe siltation. The typical fault types corresponding to each concealed pipe node are collected to generate a typical fault type set.

[0062] A hidden pipe node is selected from the fault propagation path, and a fault assumption condition is selected from the set of typical fault types. Then, the physical parameters corresponding to the hidden pipe node in the digital twin simulation model are adjusted according to the selected fault assumption condition type. Specifically, when the fault assumption condition is pipe siltation, the effective flow area of ​​the hidden pipe node is reduced; when the fault assumption condition is water seal failure, the water seal depth of the hidden pipe node is reduced; and when the fault assumption condition is hidden leakage, the permeability coefficient of the drop layer of the hidden pipe node is increased. Each fault assumption condition is applied to each hidden pipe node on the fault propagation path in sequence, and the corresponding physical parameters are adjusted accordingly.

[0063] In the digital twin simulation model, after updating the physical parameters of the concealed pipeline nodes under the applied fault assumption conditions, the operational status changes of each downstream concealed pipeline node under these fault assumption conditions are simulated step-by-step downstream along the fault propagation path. Based on the updated physical parameters and the pipe segment flow regime deduction formula, the digital twin simulation model sequentially calculates the simulated flow rate and simulated pipe wall pressure data for each downstream concealed pipeline node under these fault assumption conditions. The calculated simulated flow rate and simulated pipe wall pressure data are used as the simulated operational status data for each downstream node, completing the forward simulation from the node under the applied fault assumption conditions to the final node.

[0064] The actual operating status data of each downstream node, including actual flow rate changes and actual pipe wall pressure, is obtained from the digital twin simulation model. Then, for each fault assumption, the relative deviation between the simulated operating status data and the actual operating status data of each downstream node is calculated. This relative deviation is obtained by dividing the absolute value of the difference between the simulated and actual data by the actual data. Next, the relative deviation values ​​are weighted and summed based on the topological distance between each downstream node and the root cause node, assigning higher weights to downstream nodes closer to the root cause node, thus generating a comprehensive deviation score for each fault assumption. Finally, the fault assumption with the smallest comprehensive deviation score is determined as the best-matching fault type, generating a positive simulation result.

[0065] Information on suspected root cause nodes and trend feature markers for each hidden pipeline node are obtained from the historical trend analysis results. Then, the fault type and fault occurrence node corresponding to the fault hypothesis with the minimum comprehensive deviation score are obtained from the forward simulation results. Next, the suspected root cause nodes are compared with the fault occurrence nodes in terms of location, and the degradation trend type of each node in the trend feature markers is compared with the fault type corresponding to the fault hypothesis to filter out fault hypotheses that are both in the same location and have the same fault type. Finally, the fault occurrence nodes, fault types, and fault propagation paths corresponding to the filtered fault hypotheses are summarized to generate the fault root cause diagnosis results.

[0066] For the first The comprehensive deviation score under the fault assumption conditions reflects the overall deviation score under the fault assumption conditions. Under certain fault assumptions, the overall deviation between the forward simulation results of the digital twin simulation model and the actual collected operating status data is considered. The smaller the comprehensive deviation score, the better the fault assumption matches the actual operating conditions.

[0067] For the first fault propagation path The index identifier of a downstream node, wherein the downstream node is a hidden pipeline node in the downstream direction of the pipeline topology where the fault assumption condition is applied, and the simulated operating status data of the node is used to compare the deviation with the actual collected operating status data.

[0068] This serves as an index identifier for the fault assumption conditions, which are a specific fault type from a set of typical fault types, including pipe siltation, water seal failure, and hidden leakage.

[0069] This represents the total number of downstream nodes along the fault propagation path, i.e., the number of all hidden pipeline nodes traversed downstream along the pipeline topology from the node where the fault assumption was applied.

[0070] This is the traversal index for all downstream nodes, used to traverse all downstream nodes during the normalized denominator calculation.

[0071] For the first The topological distance between each downstream node and the root cause node of the fault in the concealed pipeline node is the number of pipe segments traversed by the shortest path along the pipeline topology, and this parameter is obtained from the spatial topology mapping data.

[0072] In the first Under the first type of failure assumption, the first The simulated operational status data of the downstream node is obtained by applying the digital twin simulation model under the influence of the first... The fault propagation is derived by forward simulation along the fault propagation path based on the given fault assumptions.

[0073] For the first The data is the operating status data of each downstream node, which is obtained from the actual operating status data collected in the digital twin simulation model, including actual flow rate change data and actual pipe wall pressure data.

[0074] For the first The topological distance between each downstream node and the root cause node of the fault is also obtained from the spatial topology mapping data and is used to calculate the normalized denominator.

[0075] First, calculate the reciprocal of the topological distance for each downstream node. For each downstream node on the fault propagation path, obtain the topological distance between that downstream node and the root cause node from the spatial topology mapping data. Calculate the reciprocal of the topological distance. This reciprocal value represents the spatial correlation strength between the downstream node and the root cause node. The closer the nodes are in the topological distance, the larger the reciprocal value, indicating a stronger correlation between the node and the root cause node.

[0076] Then, the normalized denominator is calculated by summing the reciprocals of the topological distances of all downstream nodes along the fault propagation path. This normalized denominator is used to normalize the reciprocals of the topological distances of each downstream node, ensuring that the sum of the weights of all downstream nodes is one.

[0077] Next, the topological distance weight of each downstream node is calculated, and the first... The topological distance weight of a downstream node is obtained by dividing the inverse of the topological distance to the downstream node by the normalized denominator. This weight represents the weight ratio of the downstream node in the comprehensive deviation score. The closer the downstream node is to the root cause node, the greater the weight, indicating that the diagnostic results pay more attention to the fitting degree of the node closer to the root cause.

[0078] Then calculate the relative deviation value for each downstream node, and then... Simulated operating status data of each downstream node Subtract the actual operating status data of the downstream node, take the absolute value of the difference, and then divide it by the actual operating status data to obtain the relative deviation value of the downstream node. This relative deviation value reflects the relative deviation of the downstream node at the [missing information - likely a specific time point]. The degree of deviation between the simulated data and the actual data of the downstream node under certain fault assumptions.

[0079] Calculate the weighted deviation value for each downstream node, and then... The weighted deviation value of a downstream node is obtained by multiplying the topological distance weight of the downstream node by the relative deviation value of the downstream node. This weighted deviation value takes into account the spatial correlation strength between the downstream node and the root cause node of the fault and the degree of deviation between the simulated data and the actual data.

[0080] Finally, the comprehensive deviation score is calculated by summing the weighted deviation values ​​of all downstream nodes along the fault propagation path to obtain the score. The comprehensive deviation score is calculated under each fault assumption condition. The smaller the comprehensive deviation score, the better the forward simulation results under that fault assumption condition match the actual operating data. Finally, the fault assumption condition with the smallest comprehensive deviation score is selected as the most matching fault type.

[0081] The beneficial effects are as follows: The above steps generate a fault propagation path by tracing upstream pipeline nodes along the connectivity of concealed pipe sections from the abnormal manifestation node. This allows fault diagnosis to systematically trace the source direction of abnormal signals along the pipeline topology, improving the directionality and efficiency of fault location. Trend fitting processing of historical operating status data along the fault propagation path identifies gradual deterioration trends or abrupt abnormal jumps and generates trend feature markers. This enables fault diagnosis to analyze the evolution of the operating status of each concealed pipeline node from a time dimension. By determining the anomaly start time, the earliest concealed pipeline node with an anomaly can be identified, providing a time-dimensional analytical basis for the preliminary location of the fault root cause. Based on the concealed spatial location type, a set of typical fault types for each node is determined, and fault assumptions are sequentially applied to each concealed pipeline node along the fault propagation path for forward simulation. A comprehensive deviation score is used to calculate and select the fault assumptions that best match the actual operating conditions, avoiding the problem of inaccurate diagnosis caused by relying solely on experience. By comparing and matching historical trend analysis results with forward simulation results, and selecting consistent fault assumptions, root cause diagnosis results are generated. This achieves dual verification of historical trend analysis in the time dimension and simulation results in the spatial dimension, effectively reducing the false alarm rate and false negative rate caused by anomaly judgment from a single data source, and improving the accuracy and reliability of root cause diagnosis of hidden pipeline faults.

[0082] The operation and maintenance diagnosis report generation module 105 is used to generate a fault diagnosis report of the same-floor drainage system based on the fault root cause diagnosis results and the full-cycle data traceability chain of the corresponding hidden pipe nodes, and push the fault diagnosis report to the operation and maintenance terminal of the same-floor drainage system.

[0083] In this embodiment of the invention, when the operation and maintenance diagnosis report generation module executes the full-cycle data tracing chain based on the fault root cause diagnosis results and the corresponding concealed pipe nodes to generate a fault diagnosis report for the same-floor drainage system, and pushes the fault diagnosis report to the operation and maintenance terminal of the same-floor drainage system, it is specifically used for: The concealed pipe routing information and engineering background data in the root cause diagnosis results are integrated to generate a fault diagnosis report for the same-floor drainage system. The fault diagnosis report is pushed to the operation and maintenance terminal of the same-floor drainage system, and the corresponding maintenance entrance location and maintenance path guidance are marked in the fault diagnosis report according to the concealed space location type marked in the concealed pipe routing information.

[0084] The concealed pipeline routing information between the root cause node and the abnormal manifestation node is extracted from the fault root cause diagnosis results. This concealed pipeline routing information includes the type of concealed space traversed by each pipe segment and the connection sequence of the pipe segments. Then, the design parameters and construction records corresponding to the fault root cause node are extracted from the full-cycle data tracing chain to reconstruct the pipe material, pipe diameter specifications, and installation process information of that node, generating engineering background data for the fault location. Finally, the concealed pipeline routing information and the engineering background data are integrated with the fault type, fault occurrence node, and fault propagation path from the fault root cause diagnosis results to generate a fault diagnosis report containing precise location of the fault root cause node, reconstruction of the concealed pipeline routing, historical maintenance trajectories, and maintenance plan suggestions.

[0085] The fault diagnosis report is pushed to the maintenance terminal of the same-floor drainage system via wired or wireless network, allowing maintenance personnel to view complete fault diagnosis information. Then, based on the concealed space location type of each pipe segment marked in the concealed pipe routing information, the corresponding maintenance access location of the concealed space is marked in the fault diagnosis report. Specifically, pipe segments within the lowered floor area are marked with ground-level maintenance access locations, pipe segments within the false wall area are marked with false wall maintenance doors, and pipe segments within the suspended ceiling area are marked with suspended ceiling maintenance access locations. Finally, based on the pipe routing relationship between the maintenance access location and the root cause node of the fault, the maintenance path guide from the maintenance access point to the root cause node is marked in the fault diagnosis report, providing maintenance personnel with a clear maintenance direction and operation sequence.

[0086] The beneficial effects are as follows: By integrating the concealed pipeline routing information and engineering background data with the root cause diagnosis results to generate a fault diagnosis report, the above steps enable maintenance personnel to obtain complete information on the fault location at once, including the fault type, pipeline routing, material specifications, and installation process, providing sufficient information support for developing targeted maintenance plans. Based on the concealed space location type, the fault diagnosis report marks the maintenance entry point and maintenance path guidance, enabling maintenance personnel to quickly locate the maintenance entry point into the concealed space and accurately reach the root cause node of the fault by following the maintenance path guidance, effectively reducing the location cost and damage scope of concealed pipeline maintenance.

[0087] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0088] The embodiments of this application can acquire and process relevant data based on an artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A lifecycle management system for a same-floor drainage system based on digital twins, characterized in that, The system includes a pipeline 3D modeling module, a joint traceability chain generation module, a digital twin dynamic mapping module, a reverse traceability dual verification module, and an operation and maintenance diagnostic report generation module, wherein: The pipeline 3D modeling module is used to construct a 3D information model based on the pipeline topology of a same-floor drainage system. The joint traceability chain generation module is used to perform cross-stage association binding on the same-floor drainage system based on the spatial topology mapping data in the three-dimensional information model, and generate a spatiotemporal joint traceability chain for each hidden pipe node in the same-floor drainage system. The digital twin dynamic mapping module is used to dynamically map the three-dimensional information model with the operating status data of each hidden pipe node to construct a digital twin simulation model of the same-floor drainage system. The reverse tracing dual verification module, when the digital twin simulation model detects an abnormal signal, traces the fault path in reverse based on the spatial topology mapping data, and performs dual verification by combining the historical data change trend in the spatiotemporal joint tracing chain with the forward simulation results of the digital twin simulation model, generating a fault root cause diagnosis result. The operation and maintenance diagnosis report generation module is used to generate a fault diagnosis report for the same-floor drainage system based on the fault root cause diagnosis results and the full-cycle data traceability chain of the corresponding hidden pipe nodes, and push the fault diagnosis report to the operation and maintenance terminal of the same-floor drainage system.

2. The lifecycle management system for a same-floor drainage system based on digital twins as described in claim 1, characterized in that, When the pipeline 3D modeling module executes the construction of a 3D information model based on the pipeline topology of the same-floor drainage system, it is specifically used for: Based on the topological structure type of the same-floor drainage system, identify the hidden spatial location type of each hidden pipe node, and establish an inclusion mapping relationship between each hidden pipe node and the hidden spatial location type; Based on the aforementioned mapping relationship, hierarchical spatial encoding is assigned to each hidden pipeline node; The hierarchical spatial coding and the pipeline topology of each hidden pipeline node are correlated and fused to generate spatial topology mapping data and construct a three-dimensional information model.

3. The lifecycle management system for a same-floor drainage system based on digital twins as described in claim 2, characterized in that, When the joint traceability chain generation module performs cross-stage association binding on the same-floor drainage system using the spatial topology mapping data in the three-dimensional information model as a spatial reference, and generates a spatiotemporal joint traceability chain for each hidden pipe node in the same-floor drainage system, it is specifically used for: Using the spatial topology mapping data as the association anchor point, the multi-dimensional heterogeneous data of the same-floor drainage system is mapped and associated. The multi-dimensional heterogeneous data includes data from the planning and design stage, data from the construction and installation stage, and data from the operation and maintenance management stage. Establish a mapping relationship between the planning and design stage data and the spatial location of each concealed pipeline node to obtain the first binding mapping relationship; The construction and installation stage data and the spatial location are matched and associated to obtain a second binding mapping relationship; Establish a third binding mapping relationship between the historical fault locations in the operation and maintenance management phase data and the hierarchical spatial coding; The first binding mapping relationship, the second binding mapping relationship, and the third binding mapping relationship are merged and sorted in chronological order to form a spatiotemporal joint tracing chain for each hidden pipeline node.

4. The lifecycle management system for a same-floor drainage system based on digital twins as described in claim 1, characterized in that, When the digital twin dynamic mapping module performs dynamic twin mapping between the three-dimensional information model and the operational status data of each hidden pipe node to construct a digital twin simulation model of the same-floor drainage system, it is specifically used for: Based on the connectivity of concealed pipe segments in the spatial topology mapping data, starting from the monitoring nodes of each concealed pipe node, non-monitoring nodes are identified along the pipe topology to generate a set of non-monitoring nodes. Based on the preset pipe segment flow pattern deduction formula, flow pattern deduction is performed on the set of non-monitoring nodes to obtain the simulated operating status data of the non-monitoring nodes; The operational status data of each concealed pipe node and the simulated operational status data are input into the corresponding concealed pipe node in the three-dimensional information model to drive the status parameters of each concealed pipe node to be updated synchronously in real time. Based on the updated status parameters, a digital twin simulation model of the same-floor drainage system is constructed.

5. A lifecycle management system for a same-floor drainage system based on digital twins as described in claim 4, characterized in that, The preset flow regime deduction formula for the pipe section is as follows: ； in, This serves as an index identifier for adjacent monitoring nodes. This serves as the index identifier for non-monitored nodes. For the first Simulated operational status data of non-monitoring nodes, For the first Traffic data from adjacent monitoring nodes For the first Manning roughness coefficient at each non-monitoring node For the first Manning roughness coefficient at adjacent monitoring nodes For the first The cross-sectional area of ​​water flow at each non-monitoring node For the first The cross-sectional area of ​​water flow at each adjacent monitoring node For the first Hydraulic radius at each non-monitoring node For the first Hydraulic radius at adjacent monitoring nodes For the first Pipeline bottom slope at non-monitoring nodes For the first The pipeline bottom slope at each adjacent monitoring node.

6. The lifecycle management system for a same-floor drainage system based on digital twins as described in claim 1, characterized in that, When the digital twin simulation model detects an abnormal signal, the reverse tracing dual verification module traces the fault path backward based on the spatial topology mapping data and performs dual verification by combining the historical data change trends in the spatiotemporal joint tracing chain with the forward simulation results of the digital twin simulation model to generate a fault root cause diagnosis result. Specifically, this module is used for: When the digital twin simulation model detects an abnormal signal, it traces back to the upstream pipeline node based on the abnormal behavior node in the hidden pipeline node and the connection relationship of the hidden pipeline segment in the spatial topology mapping data, thus generating a fault propagation path. Based on the spatiotemporal joint tracing chain, the temporal change trend of historical operating status data in each hidden pipeline node is analyzed along the fault propagation path to generate historical trend analysis results. In the digital twin simulation model, different fault assumptions are applied to each hidden pipeline node on the fault propagation path for forward simulation and deduction, generating forward simulation results under each fault assumption condition; The historical trend analysis results are compared and matched with the forward simulation results to filter out the fault assumptions that are consistent between the two, and generate the root cause diagnosis results of the fault.

7. The lifecycle management system for a same-floor drainage system based on digital twins as described in claim 6, characterized in that, The reverse tracing dual verification module, when executing the spatiotemporal joint tracing chain based on the fault propagation path, analyzes the time change trend of historical operating status data in each hidden pipeline node and generates historical trend analysis results, is specifically used for: From the spatiotemporal joint tracing chain, the historical flow change data and historical pipe wall pressure data on the fault propagation path are subjected to trend fitting processing to identify whether there is a gradual deterioration trend or a sudden abnormal jump in the operating status data of each hidden pipe node, and generate trend feature markers for each hidden pipe node. Based on the trend feature markers, the abnormal start time of each hidden pipeline node is determined, the hidden pipeline node with the earliest abnormal start time is marked as a suspected root cause node, and the historical trend analysis results are generated.

8. The lifecycle management system for a same-floor drainage system based on digital twins as described in claim 7, characterized in that, When the reverse tracing dual verification module executes forward simulation in the digital twin simulation model, applying different fault assumptions to each hidden pipeline node along the fault propagation path and generating forward simulation results under each fault assumption, it is specifically used for: Based on the concealed spatial location type of each concealed pipe node in the spatial topology mapping data, a set of typical fault types for each node is determined, including pipe siltation, water seal failure, and concealed leakage. For each hidden pipe node on the fault propagation path, apply each fault assumption condition from the typical fault type set in sequence, and adjust the physical parameters of the corresponding hidden pipe node in the digital twin simulation model. The physical parameters include the effective flow area of ​​the pipe, the water seal depth, and the permeability coefficient of the drop plate layer. The digital twin simulation model is driven to perform forward simulation and deduction along the fault propagation path from the hidden pipeline node where the fault assumption is applied to the downstream, so as to obtain the simulated operating status data of each downstream node. The simulated operating status data of each downstream node is compared with the actual operating status data collected in the digital twin simulation model to calculate a comprehensive deviation score. The fault assumption condition with the smallest comprehensive deviation score is selected to generate a positive simulation result.

9. A lifecycle management system for a same-floor drainage system based on digital twins as described in claim 8, characterized in that, The formula for calculating the comprehensive deviation score is as follows: ； in, For the first Comprehensive deviation score under various failure assumptions. For the first fault propagation path The index identifier of each downstream node. This serves as an index identifier for the fault assumption conditions. This represents the total number of downstream nodes along the fault propagation path. For the traversal index of all downstream nodes, For the first The topological distance between each downstream node and the root cause node of the fault in the concealed pipeline node. In the first Under the first type of failure assumption, the first Simulated operating status data of each downstream node For the first The operational status data of each downstream node. For the first The topological distance between each downstream node and the root cause node of the fault.

10. A lifecycle management system for a same-floor drainage system based on digital twins as described in claim 1, characterized in that, When the maintenance diagnosis report generation module executes the full-cycle data tracing chain based on the fault root cause diagnosis results and the corresponding concealed pipe nodes to generate a fault diagnosis report for the same-floor drainage system, and pushes the fault diagnosis report to the maintenance terminal of the same-floor drainage system, it is specifically used for: The concealed pipe routing information and engineering background data in the root cause diagnosis results are integrated to generate a fault diagnosis report for the same-floor drainage system. The fault diagnosis report is pushed to the operation and maintenance terminal of the same-floor drainage system, and the corresponding maintenance entrance location and maintenance path guidance are marked in the fault diagnosis report according to the concealed space location type marked in the concealed pipe routing information.

Images