An urban underground pipe network whole life cycle intelligent management system

Abstract

The application discloses a kind of urban underground pipe network full life cycle wisdom management systems, it is related to urban underground pipe network management and wisdom operation and maintenance technical field, the system is by collecting multiple version GIS data, construction disturbance, geology environment and pipe network operation sensing data, establish structured, spatial integration underground pipe network database;Build main version pipe network model, extract pipeline topological relation, history drift and attribute consistency feature, carry out credibility and risk analysis and optimization correction;Evolution consistency factor, position drift driving index and coupling disturbance response coefficient are calculated, in combination with threshold value is evaluated, trigger early warning and strategy execution;Based on virtual sensing node carries out pipeline life and risk assessment, realize pipe network spatial position precision promotion, operation state monitoring and long-term evolution trend prediction, provide scientific basis for wisdom operation and maintenance and multi-constraint maintenance scheduling.

Description

Technical Field

[0001] This invention relates to the field of urban underground pipeline network management and intelligent operation and maintenance technology, specifically to an intelligent management system for the entire life cycle of urban underground pipeline networks. Background Technology

[0002] As a crucial component of municipal infrastructure, urban underground pipe networks provide various public services, including water supply, drainage, gas supply, heating, electricity, and telecommunications. Their operational status directly impacts urban safety and the capacity to guarantee public services. With the continuous expansion of urban areas and the increasing utilization of underground space, pipe network structures are becoming increasingly complex. The diverse types of pipelines, their deep distribution, and the significant cross-departmental management issues have led to widespread problems such as diverse data sources, inconsistent update frequencies, and inconsistent standards for historical data.

[0003] Currently, cities generally rely on geographic information databases for pipeline network management. However, due to factors such as missing historical data, independent database construction by multiple departments, differences in format standards, and data update delays, different versions of data in geographic information databases often exhibit spatial location discrepancies, missing attribute fields, and inconsistent update behaviors between versions, making it difficult to form a unified, reliable, and traceable master version pipeline network model. Furthermore, the underground environment is complex and variable. Affected by factors such as surface subsidence, vehicle loads, groundwater level fluctuations, and construction disturbances, pipelines may experience continuous structural deformation or spatial drift. Traditional monitoring methods based on single sensors are insufficient to cover invisible areas, resulting in some safety risks failing to be identified in a timely manner.

[0004] Furthermore, the existing pipeline network operation and maintenance system still relies mainly on manual inspections and localized monitoring, with limited comprehensive analysis capabilities for operational status such as pressure, flow, leakage, and temperature. It also lacks a unified model to support the lifespan prediction and risk assessment of aging pipelines, failing to meet the requirements of the public service sector for the continuous and stable operation of critical infrastructure such as water supply, energy supply, and communication. Therefore, there is an urgent need for an intelligent system for the full lifecycle management of urban underground pipeline networks. This system should enhance the reliability and timeliness of geographic information databases through multi-source data fusion, version alignment, real-time sensing, and virtual inference technologies, enabling refined monitoring and risk warning of pipeline network status to support the safe and reliable operation of urban public services. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a smart management system for the entire lifecycle of urban underground pipeline networks, in order to solve the problems mentioned in the background section.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a smart management system for the entire lifecycle of urban underground pipe networks, comprising:

[0007] The data acquisition module obtains geometric offset Gdev, attribute missing rate Amiss, timestamp fluctuation Tvar, and update intensity USF by parsing historical and multi-version GIS data; monitors construction activities in urban underground spaces and pipeline disturbance processes, and collects construction disturbance time series Tj; monitors underground environmental disturbance factors, and collects surface subsidence Dz, road load Lw, and groundwater level Hw; and monitors the physical state of the pipeline network during operation, and collects pipeline pressure Pt, flow rate Ft, leakage value St, and temperature Tt.

[0008] The data preprocessing module is used to unify the format, correct the location, complete the attributes and restore the time evolution of the multi-source basic data set; to synchronously process the data of the construction disturbance data set and the geological environment data set; to perform continuity and physical quantity calibration on the data of the pipeline network operation perception data set; and finally to build a structured, spatially integrated urban underground pipeline network geographic information database.

[0009] The master version pipeline network model building module is used to construct a unified master version pipeline network model based on the urban underground pipeline network geographic information database through multi-source data fusion and version alignment; and extract pipeline spatial topology relationships, historical drift, attribute consistency and update behavior characteristics, conduct credibility deviation and potential risk analysis, and perform enhancement correction and optimization to output risk prediction and operation and maintenance decisions.

[0010] The evolutionary consistency assessment module is used to extract the geometric offset Gdev, attribute missing rate Amiss, timestamp distribution fluctuation Tvar, and update sequence strength factor USF of each version model, calculate the evolutionary consistency factor ECFv, and compare it with the evolutionary consistency threshold Eth to determine whether the current version data is reliable. If it is not reliable, an appropriate strategy is given.

[0011] The pipeline spatial drift identification module is used to extract surface subsidence Dz, road load change Lw, groundwater level Hw and construction disturbance time series Tj, calculate the location drift driving index RDI, and compare it with the location drift driving threshold Rth to determine whether the pipeline location drift meets the specifications. If it does not meet the requirements, the module will provide corresponding strategies and generate a dataset of the pipeline's estimated location interval.

[0012] The virtual sensing pipeline life assessment module is used to correct the real-time pressure value Pt, real-time flow value Ft, real-time leakage value St, and real-time temperature value Tt at the location of the virtual sensing node based on the pipeline's estimated location interval dataset and using topology inference and spatial interpolation methods. The corrected pressure value Ptx, flow value Ftx, leakage value Stx, and temperature value Ttx are obtained. The coupling disturbance response coefficient CRR is calculated and compared with the coupling disturbance response threshold Cth to determine whether the virtual node area is stable. If it is unstable, an appropriate strategy is applied.

[0013] Preferably, the data acquisition module includes a multi-source basic data acquisition unit, a construction disturbance acquisition unit, a geological environment monitoring unit, and an operation sensing unit;

[0014] The multi-source basic data acquisition unit is used to monitor historical data, GIS data, and multi-department version data of the urban underground pipe network. Through multi-source data access interfaces, data comparison algorithms, and timestamp parsing technology, it sequentially performs multi-version data parsing, structural field extraction, and geometric data comparison. Using a geometric topology comparison algorithm, it analyzes the spatial differences in the geometric morphology of the pipe network from different years and departments, acquiring the geometric offset Gdev of each version model. Using field consistency verification technology, it performs field comparison and missing data statistics on the multi-source pipeline attribute tables, collecting the attribute missing information for each version of data and obtaining the attribute missing rate Amiss. Using time tag parsing and update frequency analysis methods, it collects the timestamp distribution and update cycle characteristics of different versions of data, obtaining the timestamp distribution fluctuation Tvar. Using a data version update log parser and construction update record comparison technology, it collects the update behavior sequence and update frequency characteristics of each version of data, obtaining the update sequence intensity factor USF. Finally, it establishes a multi-source basic data group.

[0015] The construction disturbance acquisition unit is used to monitor construction activities in urban underground space and the disturbance process of pipelines. Through engineering excavation log acquisition equipment, road construction record monitoring system and time-series disturbance analysis method, it collects the operation time series that causes disturbance to the target pipeline, obtains the construction disturbance time series Tj, and establishes a construction disturbance data group.

[0016] The geological environment monitoring unit is used to monitor underground environmental disturbance factors by deploying surface subsidence monitoring instruments, road load monitoring equipment, groundwater level monitoring equipment, and geological sensing nodes; it uses InSAR remote sensing technology to extract subsidence changes through surface subsidence monitoring instruments to obtain surface subsidence Dz; it uses traffic pressure sensing technology and vehicle impact load identification technology to collect road surface load data to obtain road load changes Lw; it uses groundwater level monitoring wells, hydrological monitoring probes, and dynamic water level sampling modules to collect groundwater level changes to obtain groundwater level Hw; and it establishes a geological environment data set.

[0017] The operational sensing unit is used to monitor the physical state of the pipeline network during operation by deploying pressure sensors, flow meters, leakage monitoring devices, cable temperature monitors, and health monitoring equipment; to collect real-time pressure values ​​Pt using pressure sensors and pipe pressure fluctuation analysis technology; to collect real-time flow values ​​Ft using electromagnetic flow meters, ultrasonic flow meters, and flow fluctuation detection methods; to collect leakage anomaly signals and obtain real-time leakage values ​​St using acoustic leakage detection devices, soil moisture content sensing nodes, and pipe wall stress change detection methods; and to collect real-time temperature values ​​Tt inside the pipeline using cable temperature sensors, thermocouples, and temperature rise change monitoring technology; and to establish an operational sensing data set.

[0018] Preferably, the data preprocessing module includes a multi-source data processing unit, a construction disturbance geological environment processing unit, an operation perception data processing unit, and a database establishment unit;

[0019] The multi-source data processing unit is used to preprocess the data of the multi-source basic data group using multi-version data parsing methods, spatial geometric calibration technology, attribute consistency correction algorithm and time series smoothing processing method;

[0020] The construction disturbance geological environment processing unit is used to perform time-series fusion and noise filtering on the construction disturbance data group and the geological environment data group through time-series disturbance cleaning method, settlement-load-water level time-series alignment technology and noise removal method.

[0021] The operation sensing data processing unit is used to continuously repair and calibrate the physical quantities of the pipeline operation sensing data group through pressure fluctuation filtering algorithm, flow anomaly detection model and wavelet threshold denoising technology;

[0022] The database establishment unit is used to establish a structured, spatially integrated urban underground pipeline geographic information database after data preprocessing by the multi-source data processing unit, the construction disturbance geological environment processing unit, and the operation perception data processing unit.

[0023] Preferably, the master version pipeline network model building module is used to construct an initial master version model for the full life cycle management of urban underground pipeline networks through multi-source data fusion and version alignment methods. It uses multi-source basic data, construction disturbance data, geological environment data, and operational perception data from the urban underground pipeline network geographic information database as input. The module performs spatial topology reconstruction and attribute merging on the initial master version model to generate a unified master version pipeline network model. Simultaneously, it extracts spatial topological relationships between pipelines, historical drift trajectories, attribute field consistency, and update behavior characteristics to form an intermediate layer feature vector. This vector is used to identify the reliability deviation of version data, potential drift trends, and abnormal operation risks. The feature information is then used to enhance, correct, and optimize the master version pipeline network model, improving the ability to identify the accuracy of pipeline spatial location, the integrity of operational status, and long-term evolution trends, and outputting risk predictions and operation and maintenance decisions.

[0024] Preferably, the evolutionary consistency assessment module includes a first calculation unit and a first analysis unit;

[0025] The first calculation unit is used to extract the geometric offset Gdev, attribute missing rate Amiss, timestamp distribution fluctuation Tvar, and update sequence intensity factor USF of each version model in the urban underground pipe network geographic information database. After dimensionless processing, the evolution consistency factor ECFv is calculated and obtained.

[0026] Preferably, the first analysis unit is used to obtain a first evaluation result by comparing the evolutionary consistency factor ECFv with the evolutionary consistency threshold Eth through a preset evolutionary consistency threshold Eth:

[0027] When the evolutionary consistency factor ECFv is greater than or equal to the evolutionary consistency threshold Eth, it indicates that the current version of the data is of acceptable reliability and is included in the main version pipeline model.

[0028] When the evolutionary consistency factor ECFv is less than the evolutionary consistency threshold Eth, it indicates that the current version of the data is not trustworthy, triggering the first warning instruction and generating the first strategy: perform field-level attribute completion, geometric deviation correction, and update behavior sequence adjustment on the current version of the data; after correction, recalculate until the evolutionary consistency factor ECFv is greater than or equal to the evolutionary consistency threshold Eth.

[0029] Preferably, the pipeline space drift identification module includes a second calculation unit and a second analysis unit;

[0030] The second calculation unit is used to extract the surface settlement Dz, road load change Lw, groundwater level Hw, and construction disturbance time series Tj. After dimensionless processing, the position drift driving index RDI is calculated and obtained.

[0031] Preferably, the second analysis unit is used to obtain a second evaluation result by comparing the position drift driving index RDI with the position drift driving threshold Rth using a preset position drift driving threshold Rth:

[0032] When the position drift driving index RDI < position drift driving threshold Rth, it indicates that the pipeline position drift meets the specifications, the pipeline geometry is stable, and continuous monitoring is required.

[0033] When the position drift driving index RDI is greater than or equal to the position drift driving threshold Rth, it indicates that the pipeline position drift exceeds the specification requirements, and there is a risk of pipeline collision, leakage, excavation construction conflict or long-term operational safety. This triggers a second warning instruction and generates a second strategy: inferring the drift trend of invisible pipe segments based on the time-series perturbation backtracking model; performing three-dimensional spatial correction on the main version of the pipeline network model to correct the positions of pipeline nodes and segments; outputting the estimated pipeline position interval and correction report, and generating a pipeline estimated position interval dataset including pipeline node ID and segment ID, three-dimensional position after spatial coordinate correction, position confidence, drift interval, correction timestamp and version identifier.

[0034] Preferably, the virtual sensing pipeline life assessment module includes a third calculation unit and a third analysis unit;

[0035] The third calculation unit is used to correct the real-time pressure value Pt, real-time flow value Ft, real-time leakage value St and real-time temperature value Tt at the location of the virtual sensing node based on the pipeline estimated location interval dataset, using topological inference and spatial interpolation methods. After dimensionless processing, the coupling disturbance response coefficient CRR is calculated and obtained.

[0036] Preferably, the third analysis unit is used to obtain a third evaluation result by comparing the coupled perturbation response coefficient CRR with the coupled perturbation response threshold Cth through a preset coupled perturbation response threshold Cth:

[0037] When the coupling perturbation response coefficient CRR is less than the coupling perturbation response threshold Cth, it indicates that the virtual node region is stable, the current grid state is maintained, and continuous monitoring is performed.

[0038] When the coupling disturbance response coefficient CRR is greater than or equal to the coupling disturbance response threshold Cth, it indicates that the virtual node area is unstable and there is a risk of accelerated local corrosion or leakage due to aging factors, triggering the third early warning instruction and generating the third strategy: Based on the topological location of the virtual sensing node and the status of the surrounding pipelines, topological state inversion and spatial interpolation algorithms are used to infer the structural or operational anomalies in the unmarked areas; by comprehensively considering the time-series changes in pipeline pressure, flow, leakage, and temperature, and combining historical operation records and construction disturbance information, the master version pipeline model is used to perform life and risk assessment calculations to obtain the local life and risk index of each virtual node segment; based on the assessment results, the remaining usable life range and risk level are determined, and potential structural anomalies or leakage risk areas are marked; the generated life and risk assessment report is used for multi-constraint collaborative maintenance scheduling, including maintenance priority ranking, construction plan optimization, and risk prevention and control.

[0039] This invention provides a smart management system for the entire lifecycle of urban underground pipeline networks. It has the following beneficial effects:

[0040] (1) This intelligent management system for the entire life cycle of urban underground pipe networks uses methods such as multi-version data parsing, geometric topology comparison, attribute consistency verification and time tag reconstruction to structurally integrate multi-source basic data from different departments, different years and different formats to form a highly reliable urban underground pipe network geographic information database, providing accurate and unified data foundation for public service departments; it can accurately obtain geometric offset Gdev, attribute missing rate Amiss, timestamp distribution fluctuation Tvar and update sequence intensity factor USF, greatly reducing the risk of misjudgment caused by data fragmentation, field inconsistency and time sequence disorder, and providing a reliable data foundation for the entire life cycle management of pipe networks.

[0041] (2) This intelligent management system for the entire life cycle of urban underground pipe networks, through the temporal alignment technology of settlement-load-water level and the construction disturbance cleaning method, synchronously integrates multiple disturbance factors such as Dz, Lw, Hw, and Tj, which can accurately characterize the comprehensive impact of the underground environment on pipelines and improve the calculation accuracy of the position drift driving index (RDI). This invention can identify potential displacement risks caused by settlement, traffic impact, groundwater level changes, or construction in advance, and significantly improve the early warning capability for pipeline collisions, leaks, and operational safety hazards.

[0042] (3) This intelligent management system for the entire life cycle of urban underground pipe networks constructs a master version pipe network model through multi-source data fusion and version alignment, and performs enhanced corrections by combining historical drift, attribute consistency and update behavior characteristics, which can dynamically eliminate the cumulative deviations caused by differences between multiple versions. The corrected master version model has higher spatial location accuracy, attribute completeness and operational status consistency, and can be directly used for subsequent risk prediction and operation and maintenance decisions, thereby realizing a unified pipe network benchmark across departments and time series.

[0043] (4) This intelligent management system for the entire life cycle of urban underground pipe networks utilizes topology inference and spatial interpolation methods to construct virtual sensing nodes. Based on operating parameters such as pressure Pt, flow rate Ft, leakage St, and temperature Tt, it calculates the coupling disturbance response coefficient CRR, enabling the inference of operating status and life prediction in areas without monitoring points. After risk assessment in conjunction with the main version of the pipe network model, the remaining lifespan range and risk level can be obtained, solving the problem that traditional monitoring cannot cover concealed pipe sections, deeply covered pipe sections, and old pipe sections, and significantly improving the ability of full-area monitoring and proactive operation and maintenance of underground pipe networks. Attached Figure Description

[0044] Figure 1 This is a flowchart of a smart management system for the entire life cycle of urban underground pipe networks according to the present invention. Detailed Implementation

[0045] 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.

[0046] Example 1

[0047] Please see Figure 1 This invention provides a smart management system for the entire lifecycle of urban underground pipeline networks, comprising:

[0048] The data acquisition module obtains geometric offset Gdev, attribute missing rate Amiss, timestamp fluctuation Tvar, and update intensity USF by parsing historical and multi-version GIS data; monitors construction activities in urban underground spaces and pipeline disturbance processes, and collects construction disturbance time series Tj; monitors underground environmental disturbance factors, and collects surface subsidence Dz, road load Lw, and groundwater level Hw; and monitors the physical state of the pipeline network during operation, and collects pipeline pressure Pt, flow rate Ft, leakage value St, and temperature Tt.

[0049] The data preprocessing module is used to unify the format, correct the location, complete the attributes and restore the time evolution of the multi-source basic data set; to synchronously process the data of the construction disturbance data set and the geological environment data set; to perform continuity and physical quantity calibration on the data of the pipeline network operation perception data set; and finally to build a structured, spatially integrated urban underground pipeline network geographic information database.

[0050] The master version pipeline network model building module is used to construct a unified master version pipeline network model based on the urban underground pipeline network geographic information database through multi-source data fusion and version alignment; and extract pipeline spatial topology relationships, historical drift, attribute consistency and update behavior characteristics, conduct credibility deviation and potential risk analysis, and perform enhancement correction and optimization to output risk prediction and operation and maintenance decisions.

[0051] The evolutionary consistency assessment module is used to extract the geometric offset Gdev, attribute missing rate Amiss, timestamp distribution fluctuation Tvar, and update sequence strength factor USF of each version model, calculate the evolutionary consistency factor ECFv, and compare it with the evolutionary consistency threshold Eth to determine whether the current version data is reliable. If it is not reliable, an appropriate strategy is given.

[0052] The pipeline spatial drift identification module is used to extract surface subsidence Dz, road load change Lw, groundwater level Hw and construction disturbance time series Tj, calculate the location drift driving index RDI, and compare it with the location drift driving threshold Rth to determine whether the pipeline location drift meets the specifications. If it does not meet the requirements, the module will provide corresponding strategies and generate a dataset of the pipeline's estimated location interval.

[0053] The virtual sensing pipeline life assessment module is used to correct the real-time pressure value Pt, real-time flow value Ft, real-time leakage value St, and real-time temperature value Tt at the location of the virtual sensing node based on the pipeline estimated location interval dataset and using topology inference and spatial interpolation methods. It calculates and obtains the coupling disturbance response coefficient CRR and compares it with the coupling disturbance response threshold Cth to determine whether the virtual node area is stable. If it is unstable, it provides an appropriate strategy.

[0054] In this embodiment, by constructing a structured and spatially integrated urban underground pipeline network geographic information database, and combining multi-source data acquisition, construction disturbance and geological environment monitoring, and pipeline operation perception, a comprehensive assessment of pipeline geometric offset, attribute loss, temporal evolution, and operational status can be achieved. This enables accurate identification of pipeline spatial drift, potential risks, and lifespan changes, providing scientific and efficient decision support for the safe operation, maintenance scheduling, and public services of urban underground pipeline networks.

[0055] Example 2

[0056] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, the data acquisition module includes a multi-source basic data acquisition unit, a construction disturbance acquisition unit, a geological environment monitoring unit, and an operation sensing unit;

[0057] The multi-source basic data acquisition unit is used to monitor historical data, GIS data, and multi-department version data of the urban underground pipe network. Through multi-source data access interfaces, data comparison algorithms, and timestamp parsing technology, it sequentially performs multi-version data parsing, structural field extraction, and geometric data comparison. Using a geometric topology comparison algorithm, it analyzes the spatial differences in the geometric morphology of the pipe network from different years and departments, collecting the geometric offset Gdev of each version model. Based on the historical data, GIS data, and multi-department version pipe network model data of the urban underground pipe network accessed by the multi-source basic data acquisition unit, it first uses a unified spatial reference system and coordinate system... Using the benchmark as a constraint, coordinate system unification and scale normalization are performed on various versions of pipeline network models formed in different years and by different departments to eliminate overall offset errors caused by differences in projection methods and survey benchmarks. Based on this, the main version of the pipeline network model or the latest and most complete version in time is used as the reference model. Pipeline node-pipe segment topology matching and geometric registration techniques are employed to perform one-to-one matching of pipeline nodes, pipe segment centerlines, and key feature points in each version of the model to be evaluated, constructing cross-version geometric correspondences. Subsequently, based on the geometric topology comparison algorithm, successfully matched nodes with the same name, pipe segments with the same number, or those with the highest spatial overlap are identified. For pipeline objects, the positional differences in three-dimensional space are calculated. These spatial differences are quantified using indicators such as Euclidean distance of node coordinates, average offset of pipe segment centerlines, and offset vectors of pipe segment endpoints. Furthermore, for pipe segments with local bends, shape adjustments, or fracture reconstructions, a line feature registration method based on shortest distance search and shape similarity constraints is introduced to calculate the average minimum or maximum offset distance between the centerlines of the two versions of the pipe segment, reflecting complex geometric changes. Finally, the above node-level and pipe segment-level geometric offsets are statistically summarized and weighted and fused according to pipe segment length, node importance, or topological level to obtain... The geometric offset Gdev, representing the overall spatial consistency of the model across different versions, is used. Field consistency verification technology is employed to compare and count missing fields in the multi-source pipeline attribute table, collecting the attribute missing rate (Amiss) for each version of the data. Time stamp parsing and update frequency analysis methods are used to collect the timestamp distribution and update cycle characteristics of different versions of the data, obtaining the timestamp distribution fluctuation (Tvar). Data version update log parser and construction update record comparison technology are used to collect the update behavior sequence and update frequency characteristics of each version of the data, obtaining the update sequence intensity factor (USF). A multi-source basic data set is then established.

[0058] The construction disturbance acquisition unit is used to monitor construction activities in urban underground space and the disturbance process of pipelines. Through engineering excavation log acquisition equipment, road construction record monitoring system and time-series disturbance analysis method, it collects the operation time series that causes disturbance to the target pipeline, obtains the construction disturbance time series Tj, and establishes a construction disturbance data group.

[0059] The geological environment monitoring unit is used to monitor underground environmental disturbance factors by deploying surface subsidence monitoring instruments, road load monitoring equipment, groundwater level monitoring equipment, and geological sensing nodes; it uses InSAR remote sensing technology to extract subsidence changes through surface subsidence monitoring instruments to obtain surface subsidence Dz; it uses traffic pressure sensing technology and vehicle impact load identification technology to collect road surface load data to obtain road load changes Lw; it uses groundwater level monitoring wells, hydrological monitoring probes, and dynamic water level sampling modules to collect groundwater level changes to obtain groundwater level Hw; and it establishes a geological environment data set.

[0060] The operational sensing unit is used to monitor the physical state of the pipeline network during operation by deploying pressure sensors, flow meters, leakage monitoring devices, cable temperature monitors, and health monitoring equipment; to collect real-time pressure values ​​Pt using pressure sensors and pipe pressure fluctuation analysis technology; to collect real-time flow values ​​Ft using electromagnetic flow meters, ultrasonic flow meters, and flow fluctuation detection methods; to collect leakage anomaly signals and obtain real-time leakage values ​​St using acoustic leakage detection devices, soil moisture content sensing nodes, and pipe wall stress change detection methods; and to collect real-time temperature values ​​Tt inside the pipeline using cable temperature sensors, thermocouples, and temperature rise change monitoring technology; and to establish an operational sensing data set.

[0061] In this embodiment, through multi-source basic data acquisition, construction disturbance monitoring, geological environment perception, and real-time monitoring of pipeline operation status, comprehensive collection and quantitative analysis of geometric offset, attribute integrity, construction disturbance impact, environmental changes, and operational anomalies of urban underground pipelines are achieved. This provides accurate and reliable data support for the full life cycle management of pipelines, and improves the safety of pipeline operation, maintenance efficiency, and public service guarantee capabilities.

[0062] Example 3

[0063] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, the data preprocessing module includes a multi-source data processing unit, a construction disturbance geological environment processing unit, an operation perception data processing unit, and a database establishment unit;

[0064] The multi-source data processing unit is used to preprocess the data of the multi-source basic data group using multi-version data parsing methods, spatial geometric calibration technology, attribute consistency correction algorithms, and time series smoothing methods; it employs multi-source data structure mapping technology to perform unified field conversion and structural normalization on data from different departments and in different formats, establishing a basic field mapping relationship set; it uses a geometric topology calibration algorithm to correct the spatial position of the collected geometric offset Gdev and reconstruct the vector topology relationship to ensure the consistency of pipeline nodes, pipe segments, and ancillary structures; based on the attribute field consistency comparison model, it performs field completion, abnormal attribute removal, and multi-version attribute value conflict resolution on the attribute missing rate Amiss; and it uses timestamp distribution reconstruction technology and version sequence normalization methods to denoise and normalize the timestamp distribution fluctuation Tvar and the update sequence intensity factor USF to restore the time evolution sequence of each version of the data.

[0065] The construction disturbance geological environment processing unit is used to perform time-series fusion and noise filtering on the construction disturbance data group and the geological environment data group through time-series disturbance cleaning method, settlement-load-water level time-series alignment technology and noise removal method; to smooth the construction disturbance time series Tj; and to perform time-series synchronization and noise filtering on settlement Dz, road load Lw and groundwater level Hw, removing abnormal abrupt changes and invalid data.

[0066] The operation sensing data processing unit is used to perform continuous repair and physical quantity calibration on the pipeline operation sensing data group through pressure fluctuation filtering algorithm, flow anomaly detection model and wavelet threshold denoising technology; to denoise the pressure Pt; to correct abrupt changes in flow Ft; and to smooth the leakage value St and temperature Tt to ensure that the physical quantity data is continuous and reliable.

[0067] The database establishment unit is used to establish a structured, spatially integrated urban underground pipeline geographic information database after data preprocessing by the multi-source data processing unit, the construction disturbance geological environment processing unit, and the operation perception data processing unit.

[0068] In this embodiment, by performing unified preprocessing, time-series fusion, anomaly removal, and physical quantity calibration on multi-source basic data, construction disturbance data, geological environment data, and operational perception data, a structured and spatially integrated urban underground pipeline network geographic information database is established. This achieves unified data format, improved attribute integrity, and ensures spatiotemporal continuity, providing a high-quality and reliable data foundation for intelligent management of urban underground pipeline networks and public service decision-making.

[0069] Example 4

[0070] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1Specifically, the master version pipeline network model building module is used to construct an initial master version model for the full life cycle management of urban underground pipeline networks through multi-source data fusion and version alignment methods. It uses multi-source basic data, construction disturbance data, geological environment data, and operation perception data from the urban underground pipeline network geographic information database as inputs to perform spatial topology reconstruction and attribute merging on the initial master version model, generating a unified master version pipeline network model. At the same time, it extracts the spatial topological relationships between pipelines, historical drift trajectories, attribute field consistency, and update behavior characteristics to form an intermediate layer feature vector. This vector is used to identify the credibility deviation of version data, potential drift trends, and abnormal operation risks. The feature information is then used to enhance, correct, and optimize the master version pipeline network model, improving the ability to identify the accuracy of pipeline spatial location, the integrity of operational status, and long-term evolution trends, and outputting risk prediction and operation and maintenance decisions.

[0071] In this embodiment, a unified master version pipeline model is constructed by fusing and aligning multi-source data based on the urban underground pipeline geographic information database. The spatial topology, historical drift, attribute consistency and update behavior are analyzed and optimized, which significantly improves the accuracy of pipeline spatial location and the integrity of operation status, enhances the ability to identify long-term evolution trends, and provides scientific and reliable support for underground pipeline risk prediction and public service operation and maintenance decisions.

[0072] Example 5

[0073] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, the evolutionary consistency assessment module includes a first computing unit and a first analysis unit;

[0074] The first calculation unit is used to extract the geometric offset Gdev, attribute missing rate Amiss, timestamp distribution fluctuation Tvar, and update sequence intensity factor USF of each version model in the urban underground pipe network geographic information database. After dimensionless processing, the evolutionary consistency factor ECFv is calculated and obtained, as shown in the following formula:

[0075]

[0076] In the formula, w1, w2, w3, and w4 represent weighting coefficients, which are determined by long-term statistical analysis and engineering experience of the evolution characteristics of multiple versions of urban underground pipe network data.

[0077] : Characterizes the impact of geometric offset Gdev on the reliability of version data, has a high weight, is a key indicator, and directly reflects the contribution of the consistency of different version network models in spatial location to the construction of the main version;

[0078] The Amiss rate, representing the impact of missing attributes on the reliability of version data, has the second highest weight, reflecting the role of pipeline attribute completeness in data accuracy.

[0079] : Characterizes the impact of timestamp distribution fluctuation Tvar on the reliability of version data, accounting for a medium weight, reflecting the consistency of update sequences and time evolution of different version data;

[0080] The USF (United States Factor) characterizes the impact of the updated sequence strength factor on the reliability of version data. It has a minor weight and reflects the supplementary role of data update behavior in evolutionary consistency analysis.

[0081] By weighted fusion of geometric offset Gdev, attribute missing rate Amiss, timestamp distribution fluctuation Tvar, and update sequence intensity factor USF from different versions of the model, the evolutionary consistency of the data in each version can be quantified, providing a scientific basis for evolutionary consistency assessment and version data correction strategies.

[0082] In this embodiment, the evolutionary consistency assessment module comprehensively calculates the geometric offset, attribute missing rate, timestamp fluctuation and update sequence strength of each version of the pipeline network model to obtain the evolutionary consistency factor. This allows for a quantitative assessment of the reliability of the data version, which helps to promptly identify inconsistent or abnormal data and improve the accuracy and reliability of the urban underground pipeline network geographic information database.

[0083] Example 6

[0084] This embodiment is an explanation based on Embodiment 5. Please refer to it. Figure 1 Specifically, the first analysis unit is used to obtain a first evaluation result by comparing the evolutionary consistency factor ECFv with the evolutionary consistency threshold Eth through a preset evolutionary consistency threshold Eth:

[0085] When the evolutionary consistency factor ECFv is greater than or equal to the evolutionary consistency threshold Eth, it indicates that the current version of the data is of acceptable reliability and is included in the main version pipeline model.

[0086] When the evolutionary consistency factor ECFv is less than the evolutionary consistency threshold Eth, it indicates that the current version of the data is not trustworthy, triggering the first warning instruction and generating the first strategy: perform field-level attribute completion, geometric deviation correction, and update behavior sequence adjustment on the current version of the data; after correction, recalculate until the evolutionary consistency factor ECFv is greater than or equal to the evolutionary consistency threshold Eth.

[0087] The evolutionary consistency threshold Eth is obtained through statistical analysis of a large amount of multi-version model data of urban underground pipe networks. The distribution patterns of geometric offset Gdev, attribute missing rate Amiss, timestamp distribution fluctuation Tvar, and update sequence intensity factor USF are analyzed under different years, departments, and update frequencies. Combined with historical pipe network operation records and maintenance logs, professional technicians, referring to urban underground pipe network construction and operation standards, comprehensively determine a reasonable evolutionary consistency judgment value. Referring to relevant geographic information database management specifications and pipe network data update guidelines, a reasonable range for Eth can be obtained, which is used to effectively distinguish the credibility level of version data and ensure the accuracy and reliability of the main version pipe network model construction.

[0088] In this embodiment, the first analysis unit compares and analyzes the evolution consistency factor with the preset threshold, which can automatically determine the credibility of the version data and trigger early warning and correction strategies when the data is unqualified, thereby realizing field completion, geometric deviation correction and update sequence adjustment, so as to ensure the data integrity and reliability of the main version pipeline network model and improve the management accuracy of the urban underground pipeline network geographic information database.

[0089] Example 7

[0090] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, the pipeline space drift identification module includes a second calculation unit and a second analysis unit;

[0091] The second calculation unit is used to extract surface settlement Dz, road load change Lw, groundwater level Hw, and construction disturbance time series Tj. After dimensionless processing, the location drift driving index RDI is calculated, as shown in the following formula:

[0092]

[0093] In the formula, a1, a2, a3 and a4 represent weighting coefficients, which are determined by statistical analysis and engineering experience based on long-term monitoring data of urban underground pipe network spatial deformation mechanism and external disturbance factors.

[0094] : Characterizes the influence of surface settlement Dz on pipeline position drift, has a high weight, is the main driving factor, and directly reflects the effect of foundation settlement on pipeline geometry.

[0095] This represents the impact of road load variation Lw on pipeline drift, and has a medium weight, reflecting the long-term impact of traffic load variation on pipeline spatial location.

[0096] : Characterizes the influence of groundwater level Hw on pipeline drift, with medium weight, reflecting the effect of water level changes on soil mechanical conditions and pipeline location;

[0097] : Characterizes the impact of construction disturbance time series Tj on pipeline drift, has a minor weight, and reflects the contribution of construction disturbance to short-term pipeline displacement;

[0098] By weighted fusion of surface subsidence Dz, road load change Lw, groundwater level Hw, and construction disturbance time series Tj, the driving factors of pipeline location drift can be quantified, providing a basis for decision-making for pipeline drift risk identification and spatial correction.

[0099] In this embodiment, the second calculation unit calculates the position drift driving index (RDI) based on surface subsidence, road load changes, groundwater level, and construction disturbance sequence, thereby achieving a quantitative assessment of pipeline spatial drift. This provides a scientific basis for timely detection of potential pipeline displacement risks and helps improve the operational safety and maintenance accuracy of urban underground pipe networks.

[0100] Example 8

[0101] This embodiment is an explanation based on Embodiment 7. Please refer to it. Figure 1 Specifically, the second analysis unit is used to compare and analyze the position drift driving index RDI with the position drift driving threshold Rth through a preset position drift driving threshold, and obtain a second evaluation result including:

[0102] When the position drift driving index RDI < position drift driving threshold Rth, it indicates that the pipeline position drift meets the specifications, the pipeline geometry is stable, and continuous monitoring is required.

[0103] When the position drift driving index RDI is greater than or equal to the position drift driving threshold Rth, it indicates that the pipeline position drift exceeds the specification requirements, and there is a risk of pipeline collision, leakage, excavation construction conflict or long-term operational safety. This triggers a second warning instruction and generates a second strategy: inferring the drift trend of invisible pipe segments based on the time-series perturbation backtracking model; performing three-dimensional spatial correction on the main version of the pipeline network model to correct the positions of pipeline nodes and segments; outputting the estimated pipeline position interval and correction report, and generating a pipeline estimated position interval dataset including pipeline node ID and segment ID, three-dimensional position after spatial coordinate correction, position confidence, drift interval, correction timestamp and version identifier.

[0104] The location drift-driven threshold Rth is obtained by statistically analyzing the typical variation ranges of surface subsidence Dz, road load change Lw, groundwater level Hw, and construction disturbance time series Tj in long-term monitoring data. Combining urban underground pipeline design specifications, construction safety requirements, and historical pipeline location drift records, professional technicians comprehensively determine a reasonable threshold range. Referring to relevant urban infrastructure monitoring technical standards and geological environment monitoring specifications, a judgment value for Rth is determined to distinguish whether the pipeline location status complies with regulations and to provide timely warnings of potential structural or construction conflict risks.

[0105] In this embodiment, the second analysis unit compares the position drift driving index RDI with a preset threshold Rth to achieve automatic identification and risk warning of pipeline out-of-specification drift; at the same time, based on the time-series disturbance backtracking and three-dimensional spatial correction method, the positions of pipeline nodes and pipe segments are corrected to generate a dataset of estimated pipeline position intervals, providing accurate decision support for pipeline maintenance, construction conflict prevention and long-term operational safety.

[0106] Example 9

[0107] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, the virtual sensing pipeline life assessment module includes a third calculation unit and a third analysis unit;

[0108] The third calculation unit is used to correct the real-time pressure value Pt, real-time flow value Ft, real-time leakage value St, and real-time temperature value Tt at the location of the virtual sensing node based on the pipeline estimated location interval dataset, using topology inference and spatial interpolation methods. The corrected pressure value Ptx, flow value Ftx, leakage value Stx, and temperature value Ttx are then obtained. After dimensionless processing, the coupled disturbance response coefficient CRR is calculated, as shown in the following formula:

[0109]

[0110] In the formula, s1, s2, s3 and s4 represent weighting coefficients, which are determined by statistical analysis of long-term operating data and engineering experience on the relationship between pipeline operating status parameters and pipeline aging, corrosion and leakage risks.

[0111] The real-time pressure value Pt represents the impact of the virtual node area state. It has a high weight and is a key indicator, reflecting the contribution of abnormal pipeline pressure to local lifespan and leakage risk.

[0112] : Characterizes the impact of real-time flow value Ft on the state of virtual node area, with medium weight, reflecting the effect of flow anomalies on pipeline stability;

[0113] : Characterizes the impact of real-time leakage value St on the status of virtual node area, with a medium to high weight, reflecting the impact of local leakage or corrosion risk on pipeline life;

[0114] : Characterizes the influence of real-time temperature value Tt on the state of virtual node area, with secondary weight, reflecting the auxiliary role of temperature change in pipeline material aging and life assessment;

[0115] By weighted fusion of real-time pressure value Pt, real-time flow value Ft, real-time leakage value St, and real-time temperature value Tt, the response degree of virtual node area to disturbances can be quantified, providing a basis for local life assessment and maintenance strategy optimization.

[0116] Based on the pipeline estimated location interval dataset generated by the second analysis unit, virtual sensor nodes are mapped to the corresponding pipe segment topology in the main version of the pipeline network model, clarifying the pipe segment to which the virtual sensor node belongs, the upstream and downstream node relationships, and its axial location interval. On this basis, combined with the spatial distribution and real-time operation data of the physical sensor nodes already deployed in the main version of the pipeline network model, a topological neighborhood constraint relationship centered on the virtual sensor node is constructed. A joint correction method based on spatial interpolation and physical constraints based on the pipeline network topology is used to correct the real-time pressure value Pt, real-time flow value Ft, real-time leakage value St, and real-time temperature value Tt at the location of the virtual sensor node. Specifically, based on the real-time pressure and flow monitoring values ​​of the upstream and downstream physical nodes, combined with the axial distance, location confidence, and pipe segment structural parameters of the virtual sensor node within the estimated location interval, a topology-weighted interpolation method is used to calculate and obtain the corrected pressure value P. The leakage values ​​are calculated as follows: tx and Ftx; based on the intensity distribution of leakage signals in adjacent pipe sections and their variation characteristics along the pipe network topology, combined with soil permeability characteristics and pipe section length parameters, anomaly gradient inversion and spatial diffusion interpolation methods are used to infer the leakage value Stx at the virtual sensing node; based on the historical temperature time series data of the virtual sensing node and its neighboring nodes, combined with medium flow direction and environmental influence factors, a time window smoothing and spatial interpolation fusion method is used to calculate the corrected temperature value Ttx; subsequently, physical consistency checks based on pipe network continuity, mass conservation relationship and multi-physical quantity coupling characteristics are performed on the corrected Ptx, Ftx, Stx and Ttx, eliminating abnormal results that do not meet the constraints or triggering a recalculation mechanism, and finally obtaining the virtual sensing node operating status data that satisfies the topological and physical constraints, which serves as the effective input parameter for the coupling disturbance response coefficient CRR in the third calculation unit.

[0117] In this embodiment, the third computing unit corrects the real-time pressure, flow, leakage and temperature of the virtual sensing node based on the pipeline estimated location interval dataset and combines topological inference and spatial interpolation methods. It calculates the coupling disturbance response coefficient (CRR) to achieve accurate quantification of the local operating status and potential anomalies of the pipeline network, providing reliable data support for pipeline life assessment and risk prevention.

[0118] Example 10

[0119] This embodiment is an explanation based on Embodiment 9. Please refer to it. Figure 1 Specifically, the third analysis unit is used to obtain a third evaluation result by comparing the coupled perturbation response coefficient CRR with the coupled perturbation response threshold Cth, based on a preset coupled perturbation response threshold Cth:

[0120] When the coupling perturbation response coefficient CRR is less than the coupling perturbation response threshold Cth, it indicates that the virtual node region is stable, the current grid state is maintained, and continuous monitoring is performed.

[0121] When the coupling disturbance response coefficient CRR is greater than or equal to the coupling disturbance response threshold Cth, it indicates that the virtual node area is unstable and there is a risk of accelerated local corrosion or leakage due to aging factors, triggering the third early warning instruction and generating the third strategy: Based on the topological location of the virtual sensing node and the status of the surrounding pipelines, topological state inversion and spatial interpolation algorithms are used to infer the structural or operational anomalies in the unmarked areas; by comprehensively considering the time-series changes in pipeline pressure, flow, leakage, and temperature, and combining historical operation records and construction disturbance information, the master version pipeline model is used to perform life and risk assessment calculations to obtain the local life and risk index of each virtual node segment; based on the assessment results, the remaining usable life range and risk level are determined, and potential structural anomalies or leakage risk areas are marked; the generated life and risk assessment report is used for multi-constraint collaborative maintenance scheduling, including maintenance priority ranking, construction plan optimization, and risk prevention and control.

[0122] The coupling disturbance response threshold Cth is obtained by statistically analyzing long-term monitoring data of pressure Pt, flow rate Ft, leakage value St, and temperature Tt in the pipeline section where the virtual node is located. The distribution range of the coupling disturbance response coefficient CRR under normal operating conditions and under local aging or leakage risk conditions is extracted. Combining historical maintenance records, pipeline operation experience, and judgment by professional technicians, and referring to urban underground pipeline safety operation standards and public service water supply / drainage reliability specifications, a reasonable threshold range Cth is determined to distinguish whether the virtual node area is stable, thereby achieving local lifespan assessment and risk prevention.

[0123] In this embodiment, the third analysis unit compares the coupled disturbance response coefficient CRR with the preset threshold Cth to achieve real-time assessment of the stability and potential risks of the virtual node area. When an anomaly is detected, it can infer the structural or operational anomaly in the un-deployed area, quantify the local lifespan and risk level, and generate a multi-constraint collaborative maintenance scheduling scheme in combination with the main version of the pipeline network model, thereby improving the operational safety of the urban underground pipeline network and the scientificity and accuracy of maintenance decisions.

[0124] This specific embodiment is merely an explanation of this application and is not intended to limit it. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

Claims

1. A smart management system for the entire lifecycle of urban underground pipe networks, characterized in that, include: The data acquisition module obtains geometric offset Gdev, attribute missing rate Amiss, timestamp fluctuation Tvar, and update intensity USF by parsing historical and multi-version GIS data; it monitors construction activities in urban underground spaces and the disturbance process of pipelines, and collects the construction disturbance time series Tj. Monitor underground environmental disturbance factors, and collect data on surface subsidence (Dz), road load (Lw), and groundwater level (Hw); monitor the physical state of the pipeline network during operation, and collect data on pipeline pressure (Pt), flow rate (Ft), leakage value (St), and temperature (Tt). The data preprocessing module is used to unify the format, correct the location, complete the attributes and restore the time evolution of the multi-source basic data set; to synchronously process the data of the construction disturbance data set and the geological environment data set; to perform continuity and physical quantity calibration on the data of the pipeline network operation perception data set; and finally to build a structured, spatially integrated urban underground pipeline network geographic information database. The master version pipeline network model building module is used to construct a unified master version pipeline network model based on the urban underground pipeline network geographic information database through multi-source data fusion and version alignment; and extract pipeline spatial topology relationships, historical drift, attribute consistency and update behavior characteristics, conduct credibility deviation and potential risk analysis, and perform enhancement correction and optimization to output risk prediction and operation and maintenance decisions. The evolutionary consistency assessment module is used to extract the geometric offset Gdev, attribute missing rate Amiss, timestamp distribution fluctuation Tvar, and update sequence strength factor USF of each version model, calculate the evolutionary consistency factor ECFv, and compare it with the evolutionary consistency threshold Eth to determine whether the current version data is reliable. If it is not reliable, an appropriate strategy is given. The pipeline spatial drift identification module is used to extract surface subsidence Dz, road load change Lw, groundwater level Hw and construction disturbance time series Tj, calculate the location drift driving index RDI, and compare it with the location drift driving threshold Rth to determine whether the pipeline location drift meets the specifications. If it does not meet the requirements, the module will provide corresponding strategies and generate a dataset of the pipeline's estimated location interval. The virtual sensing pipeline life assessment module is used to correct the real-time pressure value Pt, real-time flow value Ft, real-time leakage value St, and real-time temperature value Tt at the location of the virtual sensing node based on the pipeline estimated location interval dataset and using topology inference and spatial interpolation methods. It calculates and obtains the coupling disturbance response coefficient CRR and compares it with the coupling disturbance response threshold Cth to determine whether the virtual node area is stable. If it is unstable, it provides an appropriate strategy.

2. The intelligent management system for the entire life cycle of urban underground pipeline networks according to claim 1, characterized in that, The data acquisition module includes a multi-source basic data acquisition unit, a construction disturbance acquisition unit, a geological environment monitoring unit, and an operation sensing unit; The multi-source basic data acquisition unit is used to monitor historical data, GIS data, and multi-department version data of the urban underground pipe network. Through multi-source data access interfaces, data comparison algorithms, and timestamp parsing technology, it sequentially performs multi-version data parsing, structural field extraction, and geometric data comparison. Using a geometric topology comparison algorithm, it analyzes the spatial differences in the geometric morphology of the pipe network from different years and departments, acquiring the geometric offset Gdev of each version model. Using field consistency verification technology, it performs field comparison and missing data statistics on the multi-source pipeline attribute tables, collecting the attribute missing information for each version of data and obtaining the attribute missing rate Amiss. Using time tag parsing and update frequency analysis methods, it collects the timestamp distribution and update cycle characteristics of different versions of data, obtaining the timestamp distribution fluctuation Tvar. Using a data version update log parser and construction update record comparison technology, it collects the update behavior sequence and update frequency characteristics of each version of data, obtaining the update sequence intensity factor USF. Finally, it establishes a multi-source basic data group. The construction disturbance acquisition unit is used to monitor construction activities in urban underground space and the disturbance process of pipelines. Through engineering excavation log acquisition equipment, road construction record monitoring system and time-series disturbance analysis method, it collects the operation time series that causes disturbance to the target pipeline, obtains the construction disturbance time series Tj, and establishes a construction disturbance data group. The geological environment monitoring unit is used to monitor underground environmental disturbance factors by deploying surface subsidence monitoring instruments, road load monitoring equipment, groundwater level monitoring equipment, and geological sensing nodes; it uses InSAR remote sensing technology to extract subsidence changes through surface subsidence monitoring instruments to obtain surface subsidence Dz; it uses traffic pressure sensing technology and vehicle impact load identification technology to collect road surface load data to obtain road load changes Lw; it uses groundwater level monitoring wells, hydrological monitoring probes, and dynamic water level sampling modules to collect groundwater level changes to obtain groundwater level Hw; and it establishes a geological environment data set. The operational sensing unit is used to monitor the physical state of the pipeline network during operation by deploying pressure sensors, flow meters, leakage monitoring devices, cable temperature monitors, and health monitoring equipment; to collect real-time pressure values ​​Pt using pressure sensors and pipe pressure fluctuation analysis technology; to collect real-time flow values ​​Ft using electromagnetic flow meters, ultrasonic flow meters, and flow fluctuation detection methods; to collect leakage anomaly signals and obtain real-time leakage values ​​St using acoustic leakage detection devices, soil moisture content sensing nodes, and pipe wall stress change detection methods; and to collect real-time temperature values ​​Tt inside the pipeline using cable temperature sensors, thermocouples, and temperature rise change monitoring technology; and to establish an operational sensing data set.

3. The intelligent management system for the entire life cycle of urban underground pipeline networks according to claim 1, characterized in that, The data preprocessing module includes a multi-source data processing unit, a construction disturbance geological environment processing unit, an operation perception data processing unit, and a database establishment unit. The multi-source data processing unit is used to preprocess the data of the multi-source basic data group using multi-version data parsing methods, spatial geometric calibration technology, attribute consistency correction algorithm and time series smoothing processing method; The construction disturbance geological environment processing unit is used to perform time-series fusion and noise filtering on the construction disturbance data group and the geological environment data group through time-series disturbance cleaning method, settlement-load-water level time-series alignment technology and noise removal method. The operation sensing data processing unit is used to continuously repair and calibrate the physical quantities of the pipeline operation sensing data group through pressure fluctuation filtering algorithm, flow anomaly detection model and wavelet threshold denoising technology; The database establishment unit is used to establish a structured, spatially integrated urban underground pipeline geographic information database after data preprocessing by the multi-source data processing unit, the construction disturbance geological environment processing unit, and the operation perception data processing unit.

4. The intelligent management system for the entire life cycle of urban underground pipeline networks according to claim 1, characterized in that, The master version pipeline network model building module is used to construct an initial master version model for the full life cycle management of urban underground pipeline networks through multi-source data fusion and version alignment methods. It uses multi-source basic data, construction disturbance data, geological environment data, and operation perception data from the urban underground pipeline network geographic information database as inputs to perform spatial topology reconstruction and attribute merging on the initial master version model, generating a unified master version pipeline network model. At the same time, it extracts the spatial topological relationships between pipelines, historical drift trajectories, attribute field consistency, and update behavior characteristics to form an intermediate layer feature vector. This vector is used to identify the credibility deviation of version data, potential drift trends, and abnormal operation risks. The feature information is then used to enhance, correct, and optimize the master version pipeline network model, improving the ability to identify the accuracy of pipeline spatial location, the integrity of operational status, and long-term evolution trends, and outputting risk predictions and operation and maintenance decisions.

5. The intelligent management system for the entire life cycle of urban underground pipeline networks according to claim 1, characterized in that, The evolutionary consistency assessment module includes a first calculation unit and a first analysis unit; The first calculation unit is used to extract the geometric offset Gdev, attribute missing rate Amiss, timestamp distribution fluctuation Tvar, and update sequence intensity factor USF of each version model in the urban underground pipe network geographic information database. After dimensionless processing, the evolution consistency factor ECFv is calculated and obtained.

6. The intelligent management system for the entire life cycle of urban underground pipeline networks according to claim 5, characterized in that, The first analysis unit is used to obtain a first evaluation result by comparing the evolutionary consistency factor ECFv with the evolutionary consistency threshold Eth through a preset evolutionary consistency threshold Eth: When the evolutionary consistency factor ECFv is greater than or equal to the evolutionary consistency threshold Eth, it indicates that the current version of the data is of acceptable reliability and is included in the main version pipeline model. When the evolutionary consistency factor ECFv is less than the evolutionary consistency threshold Eth, it indicates that the current version of the data is not trustworthy, triggering the first warning instruction and generating the first strategy: perform field-level attribute completion, geometric deviation correction, and update behavior sequence adjustment on the current version of the data; after correction, recalculate until the evolutionary consistency factor ECFv is greater than or equal to the evolutionary consistency threshold Eth.

7. The intelligent management system for the entire life cycle of urban underground pipeline networks according to claim 1, characterized in that, The pipeline space drift identification module includes a second calculation unit and a second analysis unit; The second calculation unit is used to extract the surface settlement Dz, road load change Lw, groundwater level Hw, and construction disturbance time series Tj. After dimensionless processing, the position drift driving index RDI is calculated and obtained.

8. The intelligent management system for the entire life cycle of urban underground pipelines according to claim 7, characterized in that, The second analysis unit is used to compare and analyze the position drift driving index RDI with the position drift driving threshold Rth to obtain a second evaluation result, including: When the position drift driving index RDI < position drift driving threshold Rth, it indicates that the pipeline position drift meets the specifications, the pipeline geometry is stable, and continuous monitoring is required. When the position drift driving index RDI is greater than or equal to the position drift driving threshold Rth, it indicates that the pipeline position drift exceeds the specification requirements, and there is a risk of pipeline collision, leakage, excavation construction conflict or long-term operational safety. This triggers a second warning instruction and generates a second strategy: inferring the drift trend of invisible pipe segments based on the time-series perturbation backtracking model; performing three-dimensional spatial correction on the main version of the pipeline network model to correct the positions of pipeline nodes and segments; outputting the estimated pipeline position interval and correction report, and generating a pipeline estimated position interval dataset including pipeline node ID and segment ID, three-dimensional position after spatial coordinate correction, position confidence, drift interval, correction timestamp and version identifier.

9. The intelligent management system for the entire life cycle of urban underground pipeline networks according to claim 1, characterized in that, The virtual sensing pipeline life assessment module includes a third calculation unit and a third analysis unit; The third calculation unit is used to correct the real-time pressure value Pt, real-time flow value Ft, real-time leakage value St, and real-time temperature value Tt at the location of the virtual sensing node based on the pipeline estimated location interval dataset and using topological inference and spatial interpolation methods. The corrected pressure value Ptx, flow value Ftx, leakage value Stx, and temperature value Ttx are obtained. After dimensionless processing, the coupling disturbance response coefficient CRR is calculated.

10. A smart management system for the entire lifecycle of urban underground pipeline networks according to claim 9, characterized in that, The third analysis unit is used to compare and analyze the coupled perturbation response coefficient CRR with the coupled perturbation response threshold Cth by setting a preset coupled perturbation response threshold Cth, and obtain the third evaluation result, including: When the coupling perturbation response coefficient CRR is less than the coupling perturbation response threshold Cth, it indicates that the virtual node region is stable, the current grid state is maintained, and continuous monitoring is performed. When the coupling disturbance response coefficient CRR is greater than or equal to the coupling disturbance response threshold Cth, it indicates that the virtual node area is unstable and there is a risk of accelerated local corrosion or leakage due to aging factors, triggering the third early warning instruction and generating the third strategy: Based on the topological location of the virtual sensing node and the status of the surrounding pipelines, topological state inversion and spatial interpolation algorithms are used to infer the structural or operational anomalies in the unmarked areas; by comprehensively considering the time-series changes in pipeline pressure, flow, leakage, and temperature, and combining historical operation records and construction disturbance information, the master version pipeline model is used to perform life and risk assessment calculations to obtain the local life and risk index of each virtual node segment; based on the assessment results, the remaining usable life range and risk level are determined, and potential structural anomalies or leakage risk areas are marked; the generated life and risk assessment report is used for multi-constraint collaborative maintenance scheduling, including maintenance priority ranking, construction plan optimization, and risk prevention and control.

Images