A cloud platform for multi-scale deformation simulation and risk prediction of urban underground pipeline networks

Abstract

The present invention relates to the field of underground pipe network leakage early warning technology, specifically a multi-scale deformation simulation and risk prediction cloud platform for urban underground pipe networks, comprising obtaining underground pipe network data of a city; dividing the city according to the city's surface coverage data to obtain urban sub-regions; performing satellite detection on the urban sub-regions to obtain dielectric feedback data and identify the dielectric diffusion direction; determining the dielectric diffusion area based on the underground pipe network data, the urban sub-regions and the dielectric diffusion direction to calculate the correlation influence coefficient; identifying the correlation influence coefficient and the dielectric diffusion direction to determine the leakage abnormality area; performing simulation based on the leakage abnormality area, the correlation influence coefficient and the dielectric feedback data to obtain pipe network leakage parameters; calculating the early warning coefficient based on the pipe network leakage parameters; and correcting the early warning coefficient and issuing an early warning based on the dielectric prediction parameters. The present invention can accurately identify and warn of leakage in urban underground pipe networks through the early warning coefficient.

Description

Technical Field

[0001] The present invention relates to the technical field of underground pipe network leakage early warning technology, and specifically to a multi-scale deformation simulation and risk prediction cloud platform for urban underground pipe networks. Background Art

[0002] Traditional underground pipe network maintenance and leak detection strategies rely primarily on manual inspections or the deployment of ground sensors in limited areas. These methods are limited in cost-effectiveness, response speed, and coverage, making them incapable of meeting the demands of refined management and proactive risk prevention for large-scale pipe networks in modern cities. This leads to inefficient allocation of maintenance resources, increased emergency response costs, and increased overall operational risks.

[0003] To improve infrastructure asset management and operational decision-making efficiency, the use of advanced data processing technologies for pipeline network condition monitoring has become a growing trend. Analysis methods based on satellite remote sensing data have made it possible to obtain large-scale, periodic information on surface dielectric properties related to underground leaks.

[0004] However, transforming raw satellite remote sensing data into reliable information that can be used for business and management decisions presents challenges. The complexity of the urban surface environment can severely impact the data processing required to extract subsurface dielectric information from satellite data, leading to high uncertainty or error in the resulting risk assessments.

[0005] To this end, a cloud platform for multi-scale deformation simulation and risk prediction of urban underground pipeline networks is proposed. Summary of the Invention

[0006] The present invention aims to provide a cloud platform for multi-scale deformation simulation and risk prediction of urban underground pipeline networks. The platform obtains underground pipeline network data of a city; divides the city into sub-regions based on its surface coverage data; performs satellite detection on the sub-regions to obtain dielectric feedback data and identify dielectric diffusion directions; determines dielectric diffusion regions based on the underground pipeline network data, urban sub-regions, and dielectric diffusion directions, calculates correlation influence coefficients; identifies the correlation influence coefficients and dielectric diffusion directions to determine abnormal leakage areas; simulates the abnormal leakage areas, correlation influence coefficients, and dielectric feedback data to obtain pipeline leakage parameters; calculates an early warning coefficient based on the pipeline leakage parameters; and modifies the early warning coefficient based on the dielectric prediction parameters to issue an early warning. The present invention can accurately identify and warn of leakage in urban underground pipeline networks through the early warning coefficients.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A cloud platform for multi-scale deformation simulation and risk prediction of urban underground pipeline networks, including:

[0009] The distribution identification module obtains the city's underground pipeline network data, including pipeline network distribution depth and pipeline network distribution area; identifies the city's surface coverage data based on satellite remote sensing data, divides the city into sub-regions;

[0010] The impact analysis module conducts satellite detection on urban sub-regions to obtain dielectric feedback data; identifies the dielectric diffusion direction based on the dielectric feedback data; determines the dielectric diffusion area based on underground pipe network data, urban sub-regions, and dielectric diffusion direction, identifies associated impact data, and calculates the associated impact coefficient;

[0011] The abnormality identification module builds a leakage area judgment model to identify the correlation influence coefficient and dielectric diffusion direction, and determine the leakage abnormality area;

[0012] The leakage warning module identifies leakage anomaly areas, correlation influence coefficients, and dielectric feedback data to obtain pipeline network leakage parameters; and calculates warning coefficients based on pipeline network leakage parameters.

[0013] The dynamic prediction module predicts based on the dielectric feedback data and the pipeline leakage parameters to obtain the dielectric prediction parameters; based on the dielectric prediction parameters, the warning coefficient is corrected and an early warning is issued.

[0014] The dielectric diffusion direction identification process is as follows: obtaining dielectric feedback data of urban sub-areas, where the dielectric feedback data is time series data; identifying the variation characteristics of the dielectric feedback data, and fitting to obtain the dielectric diffusion direction.

[0015] The associated impact data includes relative position data, soil permeability parameters, surface blocking parameters, and regional interference parameters; the process of obtaining the associated impact data is: determining the dielectric diffusion area based on underground pipeline data, urban sub-areas and dielectric diffusion direction; the relative position data is determined based on the position distribution data of the dielectric diffusion area; the soil permeability parameters are parameters in the soil of the dielectric diffusion area that affect the infiltration and propagation of water in the soil; the surface blocking parameters are the blocking parameters of the surface coverage data for satellite identification of the soil dielectric constant; the regional interference parameters are the non-pipeline leakage interference parameters of the urban sub-area itself, and the non-pipeline leakage interference parameters of the sub-areas surrounding the urban sub-area to the urban sub-area.

[0016] The calculation process of the correlation influence coefficient is:

[0017] The distance influence coefficient is calculated based on the relative position data; the soil permeability coefficient is obtained based on the soil permeability parameter identification; the surface barrier coefficient is obtained based on the surface barrier parameter identification; the regional interference coefficient is obtained based on the regional interference parameter identification; the correlation influence coefficient is calculated based on the distance influence coefficient, soil permeability coefficient, surface barrier coefficient and regional interference coefficient.

[0018] The leakage area judgment model includes a diffusion direction extension layer, a leakage range specification layer, and a leakage area identification layer;

[0019] The diffusion direction extension layer corrects and extends the dielectric diffusion direction according to the soil permeability parameters of the dielectric diffusion area to obtain diffusion direction data;

[0020] The leakage range specification layer obtains diffusion direction intersection points based on diffusion direction data of urban sub-regions, determines the leakage range based on pipe network distribution data, and uses diffusion direction intersection points within the leakage range as candidate leakage points; and calculates candidate influence weights based on the correlation influence coefficients of diffusion direction data associated with the candidate leakage points;

[0021] The leakage area identification layer performs cluster analysis based on the selected leakage points and the selected influence weights to obtain the leakage area.

[0022] The calculation process of the early warning coefficient is as follows:

[0023] A leakage anomaly simulation model is constructed to identify leakage anomaly areas, associated influence coefficients, and dielectric feedback data to obtain pipeline network leakage data, which includes leakage direction and leakage flow. An early warning coefficient is obtained based on the leakage direction and leakage flow.

[0024] The correction process of the warning coefficient is as follows: prediction is performed based on dielectric feedback data and pipeline leakage parameters to obtain dielectric prediction parameters; actual dielectric data is obtained based on satellite detection, and actual variation coefficients are obtained based on the actual dielectric data and the dielectric prediction parameters; warning correction factors are calculated based on the actual variation coefficients and associated influence coefficients of urban sub-regions; and the warning coefficients are corrected based on the warning correction factors.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] 1. The present invention determines the dielectric diffusion area based on underground pipeline network data, urban sub-areas, and dielectric diffusion direction; identifies relative position data and soil permeability parameters based on the dielectric diffusion area; determines surface barrier parameters based on surface cover data of the urban sub-area; and determines regional interference parameters based on non-pipeline network leakage interference in the urban sub-area and surrounding areas; accurately identifies the correlation data between underground pipeline network data and urban sub-areas; and calculates the correlation influence coefficient; and accurately measures the correlation relationship between underground pipeline network data and urban sub-areas.

[0027] 2. The present invention constructs a leakage area judgment model to identify the correlation influence coefficient and dielectric diffusion direction, corrects and extends the dielectric diffusion direction according to the soil permeability parameters of the dielectric diffusion area, and obtains the diffusion direction data; obtains the diffusion direction intersection according to the diffusion direction data of the urban sub-area, and determines the leakage point to be selected; calculates the influence weight to be selected based on the correlation influence coefficient of the diffusion direction data associated with the leakage point to be selected; performs cluster analysis based on the leakage point to be selected and the influence weight to be selected to obtain the leakage area, thereby accurately identifying the leakage area of the pipeline network.

[0028] 3. The present invention constructs a leakage anomaly simulation model to identify leakage anomaly areas, correlation influence coefficients and dielectric feedback data to obtain pipeline network leakage data, which includes leakage direction and leakage flow; an early warning coefficient is obtained based on the leakage direction and leakage flow; thereby accurately issuing an early warning based on the leakage situation of the pipeline network.

[0029] 4. The present invention makes predictions based on dielectric feedback data and pipeline network leakage parameters to obtain dielectric prediction parameters; obtains actual dielectric data based on satellite detection, and obtains actual variation coefficients based on the actual dielectric data and the dielectric prediction parameters; obtains early warning correction factors based on the actual variation coefficients and associated influence coefficients of urban sub-regions; and corrects the early warning coefficients based on the early warning correction factors, thereby accurately correcting the leakage changes in the pipeline network. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a schematic structural diagram of a multi-scale deformation simulation and risk prediction cloud platform for urban underground pipeline networks according to the present invention;

[0031] Figure 2 It is a structural schematic diagram of the leakage area judgment model of the present invention;

[0032] Figure 3 This is a flow chart of the acquisition and correction of the warning coefficient of the present invention. DETAILED DESCRIPTION

[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0034] Example 1

[0035] This application proposes a multi-scale deformation simulation and risk prediction cloud platform for urban underground pipeline networks, such as Figure 1 Shown, including:

[0036] The distribution identification module obtains the city's underground pipeline network data, including the pipeline network distribution depth and pipeline network distribution area; identifies the city's surface coverage data based on satellite remote sensing data, divides the city into sub-areas.

[0037] Obtain underground pipeline network data provided by urban planning departments or pipeline network operators, including but not limited to pipeline network distribution depth and pipeline network distribution area; the pipeline network distribution depth is the burial depth of the pipeline network, and the pipeline network distribution area is the geographic coordinate data of the pipeline.

[0038] The surface cover data is the coverage type data of the urban surface, including hardened road surface, vegetation cover, buildings, bare soil, etc. Different surface cover types will cause different interferences to the satellite detection signal;

[0039] Hardened pavements include cement floors and asphalt pavements. Compared with bare soil, the dielectric constant of hardened pavements is significantly different. Radar waves have limited penetration capabilities and can only obtain shallow information, which may miss deep leaks.

[0040] Vegetation-covered areas include forest parks and green belts. The dielectric constant of vegetation is related to its water content, but the canopy layer causes scattering noise. The scattered signal from the vegetation canopy overlaps with the soil seepage signal, making it difficult to separate using traditional filtering methods. Polarization decomposition is required to suppress interference. Dense forests can completely block radar waves, causing signal failure.

[0041] Building areas include facilities made of various materials, including concrete and metal structures. High-density buildings trigger multiple reflections, generating false anomaly signals. Optical imaging must be used to eliminate interference areas. Metal structures completely shield underground signals, leading to detection blind spots.

[0042] Bare soil: The dielectric baseline in the bare soil area is low, and small leaks are easy to detect, but interference from natural humidity fluctuations must be eliminated.

[0043] The urban coverage data is divided to obtain data table 1.

[0044] Table 1 City coverage data type table

[0045]

[0046] This method accurately identifies pipeline network distribution and surface cover, and then performs regional division. This lays the foundation for subsequently distinguishing satellite signal responses under different surface conditions and conducting regional impact analysis and risk assessment. It also overcomes the errors caused by the assumption of surface homogeneity in traditional methods.

[0047] The impact analysis module conducts satellite detection of urban sub-regions to obtain dielectric feedback data; identifies the dielectric diffusion direction based on the dielectric feedback data; determines the dielectric diffusion area based on underground pipeline data, urban sub-regions, and dielectric diffusion direction, identifies the associated impact data, and calculates the associated impact coefficient.

[0048] The dielectric diffusion direction identification process involves obtaining time-series dielectric feedback data for urban sub-regions, identifying the changing characteristics of the dielectric feedback data, and fitting the dielectric diffusion direction. The changing characteristics include the time delay and gradient direction of the dielectric constant value change.

[0049] Long-wave radar uses L-band electromagnetic waves. Due to their strong penetrating power, they can penetrate media such as surface vegetation and dry soil, acquiring electromagnetic scattering information from depths of 1-3 meters underground. The radar transmits electromagnetic waves toward the surface and receives echo signals (backscatter coefficients) reflected from the surface and subsurface media. Signal strength is directly related to the electrical properties of the medium, such as the dielectric constant. Water has a much higher dielectric constant than dry soil or concrete. Moist soil, due to its high water content, significantly enhances backscatter intensity.

[0050] Pipeline leaks can cause abnormally high moisture content in the surrounding soil, manifesting as a surge in the local backscatter coefficient in radar images. Using a physical model, a mathematical relationship between the backscatter coefficient and the soil dielectric constant is established, which in turn generates a dielectric constant distribution map and generates dielectric feedback data reflecting the dielectric constant of urban subregions.

[0051] Analyze the temporal evolution of dielectric feedback data within each urban subregion. For example, by calculating the time delay and gradient direction of the dielectric constant changes between adjacent pixels or regions, the propagation trend of dielectric anomalies (usually manifested as an increase in dielectric constant, indicating increased moisture content) can be identified and fitted to derive the dielectric diffusion direction, which represents the primary path of water diffusion in the soil.

[0052] The present invention identifies dielectric feedback data detected in an urban sub-region, and obtains the changing direction of the dielectric constant in the urban sub-region based on the changing characteristics of the dielectric data, thereby obtaining the dielectric diffusion direction.

[0053] The associated impact data includes relative position data, soil infiltration parameters, surface barrier parameters, and regional interference parameters. The acquisition process of the associated impact data is as follows:

[0054] Determining a dielectric diffusion area based on underground pipe network data, urban sub-regions, and dielectric diffusion directions; the dielectric diffusion area is a penetration and propagation area of pipe network leakage;

[0055] The relative position data is determined based on the position distribution data of the dielectric diffusion region;

[0056] The soil infiltration parameters are those affecting water penetration and propagation within the dielectric diffusion zone. These parameters, such as soil type, porosity, and saturated hydraulic conductivity, are obtained from geological survey data or a soil database. The soil depth within the dielectric diffusion zone is determined based on the depth of the pipe network.

[0057] The surface blocking parameter is a blocking parameter for satellite identification of soil dielectric constant using surface cover data; it includes data obtained from actual detection of urban sub-areas and theoretical dielectric data of soil under surface cover;

[0058] The regional interference parameters are the non-pipeline leakage interference parameters of the urban sub-region itself and the non-pipeline leakage interference parameters of the sub-regions surrounding the urban sub-region to the urban sub-region; they are reflected as the dielectric data change parameters of the urban sub-region in the case of non-pipeline leakage.

[0059] The present invention determines the dielectric diffusion area based on underground pipe network data, urban sub-areas and dielectric diffusion direction; identifies relative position data and soil permeability parameters based on the dielectric diffusion area; determines surface barrier parameters based on surface cover data of the urban sub-area; and determines regional interference parameters based on non-pipeline leakage interference in the urban sub-area and surrounding areas; and accurately identifies the association data between the underground pipe network data and the urban sub-area.

[0060] The calculation process of the correlation influence coefficient is:

[0061] The distance influence coefficient is calculated based on the relative position data. The distance influence coefficient reflects the distance that water diffuses from the underground pipe network to the urban sub-region. The closer the distance, the more significant the impact of underground pipe network leakage on the dielectric constant of the urban sub-region.

[0062] The soil permeability coefficient is obtained based on soil permeability parameter identification. The soil permeability coefficient reflects the influence of soil on water permeation and diffusion in the dielectric diffusion area. The larger the soil permeability coefficient, the smoother the water permeation and diffusion in it, and the more significant the impact of underground pipeline leakage on the dielectric constant of the urban sub-area.

[0063] The surface blocking coefficient is obtained based on the surface blocking parameter identification. The surface blocking coefficient reflects the degree to which the surface cover type of the urban sub-area blocks the satellite detection of the dielectric constant in the soil. It is identified based on the data difference between the satellite detection data and the actual soil data. The larger the surface blocking coefficient, the greater the degree to which the urban surface cover type blocks the satellite detection of the dielectric constant in the soil.

[0064] The regional interference coefficient is obtained based on regional interference parameter identification. The accuracy rate of dielectric data identification and judgment of pipeline leakage in urban sub-regions in the presence of regional interference parameters is used as a first accuracy rate. The accuracy rate of dielectric data identification and judgment of pipeline leakage in urban sub-regions in the absence of regional interference parameters is used as a second accuracy rate. The regional interference coefficient is determined based on the changing relationship between the first accuracy rate and the second accuracy rate.

[0065] The regional interference coefficient reflects the interference of non-leakage factors in the urban sub-region and the surrounding sub-regions, and is determined based on the accuracy of dielectric data identification and judgment of pipeline leakage in the urban sub-region with and without pipeline leakage.

[0066] The correlation influence coefficient is calculated based on the distance influence coefficient, soil permeability coefficient, surface blocking coefficient and regional interference coefficient. The calculation formula of the correlation influence coefficient is:

[0067] ;

[0068] in, represents the correlation influence coefficient; represents the distance influence coefficient; represents the soil permeability coefficient; represents the surface arresting coefficient; represents the regional interference coefficient; 、 、 and Represents the weight of each coefficient, which is obtained by collecting historical data for training and measurement.

[0069] The present invention obtains the distance influence coefficient, soil permeability coefficient, surface barrier coefficient and regional interference coefficient based on relative position data, soil permeability parameters, surface barrier parameters and regional interference parameters, and calculates the correlation influence coefficient; accurately measures the correlation relationship between underground pipeline network data and urban sub-areas.

[0070] The anomaly identification module builds a leakage area judgment model to identify the correlation influence coefficient and dielectric diffusion direction, and determine the leakage abnormal area.

[0071] The leakage area judgment model is constructed based on a deep learning network, and its structure is as follows: Figure 2 As shown; including diffusion direction extension layer, leakage range specification layer, leakage area identification layer;

[0072] The diffusion direction extension layer corrects and extends the dielectric diffusion direction according to the soil permeability parameters of the dielectric diffusion area to obtain diffusion direction data;

[0073] The leakage range specification layer obtains the diffusion direction intersection based on the diffusion direction data of the urban sub-area, determines the leakage range based on the pipe network distribution data, and takes the diffusion direction intersection within the leakage range as the candidate leakage point; the candidate influence weight is calculated based on the correlation influence coefficient of the diffusion direction data associated with the candidate leakage point; the diffusion direction data associated with the candidate leakage point is the diffusion direction data that participates in the intersection to generate the candidate leakage point.

[0074] The leakage range is determined based on the splash distance of a pipeline leak. The splash distance is the maximum range of a pipeline leak on the ground and is related to the pipeline's delivery pressure and delivery speed. The candidate impact weight is calculated by accumulating the associated impact coefficients of the diffusion direction data associated with the candidate leakage point to obtain the candidate impact coefficient; and performing normalization processing on all the candidate impact coefficients to obtain the candidate impact weight.

[0075] The leakage area identification layer performs cluster analysis based on the selected leakage points and the selected influence weights to obtain the leakage area.

[0076] In order to verify the recognition accuracy of the leakage area judgment model, it is verified; including verification model 1, verification model 2, and verification model 3; the verification model 1 is the leakage area judgment model of the present application, which extends the dielectric diffusion direction, confirms the selected leakage point, and identifies the leakage area according to the correlation influence coefficient and dielectric diffusion direction of the urban sub-area; the verification model 2 does not extend the dielectric diffusion direction and confirm the selected leakage point, and directly identifies the leakage area according to the correlation influence coefficient and dielectric diffusion direction of the urban sub-area; the verification model 3 does not divide the urban sub-area, and directly identifies the dielectric feedback data of the city for identification to obtain the leakage area;

[0077] The distance between the leakage area identified by the verification model and the actual leakage area is taken as the error distance, and the recognition accuracy is calculated based on the error distance and the preset distance threshold; the recognition accuracy value range is 0 to 1; the closer to 1, the higher the recognition accuracy. The calculation formula for the recognition accuracy is:

[0078] ;

[0079] in, Represents the recognition accuracy; Indicates the error distance; represents the distance threshold; Represents an exponential function with a natural constant as its base.

[0080] After multiple recognitions in multiple scenarios, data Table 2 is obtained.

[0081] Table 2 Leakage area judgment model verification data table

[0082]

[0083] According to the data in Table 2, the recognition accuracy of verification model 1 is the highest, that is, the identified leakage area is closest to the actual leakage area.

[0084] Through sophisticated model design, we achieve precise location of leaks from multiple uncertain diffusion clues. By comprehensively utilizing directional information, pipe network location constraints, and quantitative influencing factors, we effectively filter out noise and false alarms, significantly improving the accuracy and reliability of leak location.

[0085] The present invention constructs a leakage area judgment model to identify the correlation influence coefficient and the dielectric diffusion direction, corrects and extends the dielectric diffusion direction according to the soil permeability parameter of the dielectric diffusion area, and obtains diffusion direction data; obtains the diffusion direction intersection point according to the diffusion direction data of the urban sub-area, and determines the leakage point to be selected; calculates the influence weight to be selected according to the correlation influence coefficient of the diffusion direction data associated with the leakage point to be selected; performs cluster analysis according to the leakage point to be selected and the influence weight to be selected, and obtains the leakage area, thereby accurately identifying the leakage area of the pipeline network.

[0086] The leakage warning module identifies the leakage abnormal area based on the correlation influence coefficient and dielectric feedback data to obtain the pipeline leakage parameters; and obtains the warning coefficient based on the pipeline leakage parameters.

[0087] The process of obtaining and correcting the warning coefficient is as follows: Figure 3 As shown; the calculation process is:

[0088] A leakage anomaly simulation model is constructed to identify leakage anomaly areas, associated influence coefficients, and dielectric feedback data to obtain pipeline network leakage data, which includes leakage direction and leakage flow. An early warning coefficient is obtained based on the leakage direction and leakage flow. The leakage anomaly simulation model is trained based on the collected historical leakage data.

[0089] The warning coefficient determines the directional coefficient according to the leakage direction, and the directional coefficient is used to reflect the impact of different leakage directions on resource loss, fault repair, ecological environment, etc.; the leakage flow is identified to obtain the flow coefficient, and the flow coefficient is used to reflect the leakage degree of the pipeline network; the warning coefficient is determined according to the directional coefficient and the flow coefficient.

[0090] The present invention constructs a leakage anomaly simulation model to identify leakage anomaly areas, associated influence coefficients and dielectric feedback data to obtain pipeline network leakage data, wherein the pipeline network leakage data includes leakage direction and leakage flow; an early warning coefficient is obtained based on the leakage direction and leakage flow; thereby accurately issuing an early warning based on the leakage situation of the pipeline network.

[0091] The dynamic prediction module predicts based on the dielectric feedback data and the pipeline leakage parameters to obtain the dielectric prediction parameters; based on the dielectric prediction parameters, the warning coefficient is corrected and an early warning is issued.

[0092] The correction process of the warning coefficient is as follows: prediction is performed based on dielectric feedback data and pipeline leakage parameters to obtain dielectric prediction parameters; actual dielectric data is obtained based on satellite detection, and actual variation coefficients are obtained based on the actual dielectric data and the dielectric prediction parameters; warning correction factors are calculated based on the actual variation coefficients and associated influence coefficients of urban sub-regions; and the warning coefficients are corrected based on the warning correction factors.

[0093] The present invention performs prediction based on dielectric feedback data and pipeline network leakage parameters to obtain dielectric prediction parameters; obtains actual dielectric data based on satellite detection, and obtains actual variation coefficients based on the actual dielectric data and the dielectric prediction parameters; obtains early warning correction factors based on the actual variation coefficients and associated influence coefficients of urban sub-regions; and corrects the early warning coefficients based on the early warning correction factors, thereby accurately correcting the leakage changes in the pipeline network.

[0094] The present invention obtains underground pipe network data of a city; divides the city according to its surface coverage data to obtain urban sub-regions; performs satellite detection on the urban sub-regions to obtain dielectric feedback data and identify dielectric diffusion directions; determines dielectric diffusion area measurement and calculation correlation influence coefficients based on the underground pipe network data, urban sub-regions, and dielectric diffusion directions; identifies the correlation influence coefficients and dielectric diffusion directions to determine abnormal leakage areas; performs simulation based on the abnormal leakage areas, the correlation influence coefficients, and the dielectric feedback data to obtain pipe network leakage parameters; calculates an early warning coefficient based on the pipe network leakage parameters; corrects the early warning coefficient based on the dielectric prediction parameters and issues an early warning, thereby accurately identifying and warning leakage in the city's underground pipe network.

[0095] Example 2

[0096] This application proposes a multi-scale deformation simulation and risk prediction cloud platform for urban underground pipeline networks, such as Figure 1 Shown, including:

[0097] The distribution identification module obtains the city's underground pipeline network data, including the pipeline network distribution depth and pipeline network distribution area; identifies the city's surface coverage data based on satellite remote sensing data, divides the city into sub-areas.

[0098] Obtain underground pipeline network data provided by urban planning departments or pipeline network operators, including but not limited to pipeline network distribution depth and pipeline network distribution area; the pipeline network distribution depth is the burial depth of the pipeline network, and the pipeline network distribution area is the geographic coordinate data of the pipeline.

[0099] The surface cover data is the coverage type data of the urban surface, including hardened road surface, vegetation cover, buildings, bare soil, etc. Different surface cover types will cause different interferences to the satellite detection signal;

[0100] By accurately identifying pipeline network distribution and surface cover, and then performing regional divisions, this approach lays the foundation for distinguishing satellite signal responses under different surface conditions, as well as conducting regional impact analysis and risk assessments. This overcomes the errors introduced by traditional methods based on the assumption of surface homogeneity.

[0101] The impact analysis module conducts satellite detection of urban sub-regions to obtain dielectric feedback data; identifies the dielectric diffusion direction based on the dielectric feedback data; determines the dielectric diffusion area based on underground pipeline data, urban sub-regions, and dielectric diffusion direction, identifies the associated impact data, and calculates the associated impact coefficient.

[0102] The dielectric diffusion direction identification process is as follows: obtaining dielectric feedback data of urban sub-areas, where the dielectric feedback data is time series data; identifying the variation characteristics of the dielectric feedback data, and fitting to obtain the dielectric diffusion direction.

[0103] The present invention identifies dielectric feedback data detected in an urban sub-region, and obtains the changing direction of the dielectric constant in the urban sub-region based on the changing characteristics of the dielectric data, thereby obtaining the dielectric diffusion direction.

[0104] The associated impact data includes relative position data, soil infiltration parameters, surface barrier parameters, and regional interference parameters. The acquisition process of the associated impact data is as follows:

[0105] Determine dielectric diffusion areas based on underground pipe network data, urban sub-regions, and dielectric diffusion directions;

[0106] The relative position data is determined based on the position distribution data of the dielectric diffusion region;

[0107] The soil permeability parameters are parameters that affect water penetration and propagation in the soil in the dielectric diffusion area. Soil permeability parameters: Parameters that affect water penetration and propagation, such as soil type, porosity, and saturated hydraulic conductivity, are obtained in the dielectric diffusion area in combination with geological survey data or a soil database.

[0108] The surface blocking parameter is a blocking parameter for satellite identification of soil dielectric constant using surface cover data; it includes data obtained from actual detection of urban sub-areas and theoretical dielectric data of soil under surface cover;

[0109] The regional interference parameters are the non-pipeline network leakage interference parameters of the urban sub-region itself and the non-pipeline network leakage interference parameters of the sub-regions surrounding the urban sub-region to the urban sub-region.

[0110] The present invention determines the dielectric diffusion area based on underground pipe network data, urban sub-areas and dielectric diffusion direction; identifies relative position data and soil permeability parameters based on the dielectric diffusion area; determines surface barrier parameters based on surface cover data of the urban sub-area; and determines regional interference parameters based on non-pipeline leakage interference in the urban sub-area and surrounding areas; and accurately identifies the association data between the underground pipe network data and the urban sub-area.

[0111] The calculation process of the correlation influence coefficient is:

[0112] The distance influence coefficient is calculated based on the relative position data; the soil permeability coefficient is obtained based on the soil permeability parameter identification; the surface barrier coefficient is obtained based on the surface barrier parameter identification; the regional interference coefficient is obtained based on the regional interference parameter identification; the correlation influence coefficient is calculated based on the distance influence coefficient, soil permeability coefficient, surface barrier coefficient and regional interference coefficient.

[0113] The present invention obtains the distance influence coefficient, soil permeability coefficient, surface barrier coefficient and regional interference coefficient based on relative position data, soil permeability parameters, surface barrier parameters and regional interference parameters, and calculates the correlation influence coefficient; accurately measures the correlation relationship between underground pipeline network data and urban sub-areas.

[0114] The anomaly identification module builds a leakage area judgment model to identify the correlation influence coefficient and dielectric diffusion direction, and determine the leakage abnormal area.

[0115] The leakage area judgment model includes a diffusion direction extension layer, a leakage range specification layer, and a leakage area identification layer;

[0116] The diffusion direction extension layer corrects and extends the dielectric diffusion direction according to the soil permeability parameters of the dielectric diffusion area to obtain diffusion direction data;

[0117] The leakage range specification layer obtains diffusion direction intersection points based on diffusion direction data of urban sub-regions, determines the leakage range based on pipe network distribution data, and uses diffusion direction intersection points within the leakage range as candidate leakage points; and calculates candidate influence weights based on the correlation influence coefficients of diffusion direction data associated with the candidate leakage points;

[0118] The leakage area identification layer performs cluster analysis based on the selected leakage points and the selected influence weights to obtain the leakage area.

[0119] The present invention constructs a leakage area judgment model to identify the correlation influence coefficient and the dielectric diffusion direction, corrects and extends the dielectric diffusion direction according to the soil permeability parameter of the dielectric diffusion area, and obtains diffusion direction data; obtains the diffusion direction intersection point according to the diffusion direction data of the urban sub-area, and determines the leakage point to be selected; calculates the influence weight to be selected according to the correlation influence coefficient of the diffusion direction data associated with the leakage point to be selected; performs cluster analysis according to the leakage point to be selected and the influence weight to be selected, and obtains the leakage area, thereby accurately identifying the leakage area of the pipeline network.

[0120] The leakage warning module identifies the leakage abnormal area based on the correlation influence coefficient and dielectric feedback data to obtain the pipeline leakage parameters; and obtains the warning coefficient based on the pipeline leakage parameters.

[0121] The calculation process of the early warning coefficient is as follows:

[0122] A leakage anomaly simulation model is constructed to identify leakage anomaly areas, associated influence coefficients, and dielectric feedback data to obtain pipeline network leakage data, which includes leakage direction and leakage flow. An early warning coefficient is obtained based on the leakage direction and leakage flow.

[0123] The present invention constructs a leakage anomaly simulation model to identify leakage anomaly areas, associated influence coefficients and dielectric feedback data to obtain pipeline network leakage data, wherein the pipeline network leakage data includes leakage direction and leakage flow; an early warning coefficient is obtained based on the leakage direction and leakage flow; thereby accurately issuing an early warning based on the leakage situation of the pipeline network.

[0124] The dynamic prediction module predicts based on the dielectric feedback data and the pipeline leakage parameters to obtain the dielectric prediction parameters; based on the dielectric prediction parameters, the warning coefficient is corrected and an early warning is issued.

[0125] The correction process of the warning coefficient is as follows: prediction is performed based on dielectric feedback data and pipeline leakage parameters to obtain dielectric prediction parameters; actual dielectric data is obtained based on satellite detection, and actual variation coefficients are obtained based on the actual dielectric data and the dielectric prediction parameters; warning correction factors are calculated based on the actual variation coefficients and associated influence coefficients of urban sub-regions; and the warning coefficients are corrected based on the warning correction factors.

[0126] The present invention performs prediction based on dielectric feedback data and pipeline network leakage parameters to obtain dielectric prediction parameters; obtains actual dielectric data based on satellite detection, and obtains actual variation coefficients based on the actual dielectric data and the dielectric prediction parameters; obtains early warning correction factors based on the actual variation coefficients and associated influence coefficients of urban sub-regions; and corrects the early warning coefficients based on the early warning correction factors, thereby accurately correcting the leakage changes in the pipeline network.

[0127] The present invention obtains underground pipe network data of a city; divides the city according to its surface coverage data to obtain urban sub-regions; performs satellite detection on the urban sub-regions to obtain dielectric feedback data and identify dielectric diffusion directions; determines dielectric diffusion area measurement and calculation correlation influence coefficients based on the underground pipe network data, urban sub-regions, and dielectric diffusion directions; identifies the correlation influence coefficients and dielectric diffusion directions to determine abnormal leakage areas; performs simulation based on the abnormal leakage areas, the correlation influence coefficients, and the dielectric feedback data to obtain pipe network leakage parameters; calculates an early warning coefficient based on the pipe network leakage parameters; corrects the early warning coefficient based on the dielectric prediction parameters and issues an early warning, thereby accurately identifying and warning leakage in the city's underground pipe network.

[0128] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A multi-scale deformation simulation and risk prediction cloud platform for urban underground pipeline networks, characterized by: include: The distribution identification module obtains the city's underground pipe network data, including the pipe network distribution depth and pipe network distribution area; Identify the surface coverage data of the city based on satellite remote sensing data, divide the city into urban sub-regions; The surface coverage data is the coverage type data of the urban surface. Different surface coverage types will cause different interferences to the satellite detection signal. The impact analysis module conducts satellite detection on urban sub-regions to obtain dielectric feedback data; identifies the dielectric diffusion direction based on the dielectric feedback data; determines the dielectric diffusion area based on underground pipe network data, urban sub-regions, and dielectric diffusion direction, identifies associated impact data, and calculates the associated impact coefficient; The associated impact data includes relative position data, soil permeability parameters, surface blocking parameters, and regional interference parameters. The associated impact data is obtained by: determining the dielectric diffusion area based on underground pipe network data, urban sub-areas, and dielectric diffusion direction; the relative position data is determined based on the position distribution data of the dielectric diffusion area; the soil permeability parameter is a parameter in the soil of the dielectric diffusion area that affects the infiltration and propagation of water in the soil; the surface blocking parameter is a blocking parameter of the surface cover data for satellite identification of the soil dielectric constant; the regional interference parameter is a non-pipeline leakage interference parameter of the urban sub-area itself, and a non-pipeline leakage interference parameter of the sub-area surrounding the urban sub-area to the urban sub-area; The calculation process of the correlation influence coefficient is: The distance influence coefficient is calculated based on the relative position data; the soil permeability coefficient is obtained based on the soil permeability parameter identification; the surface barrier coefficient is obtained based on the surface barrier parameter identification; the regional interference coefficient is obtained based on the regional interference parameter identification; the correlation influence coefficient is calculated based on the distance influence coefficient, soil permeability coefficient, surface barrier coefficient and regional interference coefficient; The abnormality identification module builds a leakage area judgment model to identify the correlation influence coefficient and dielectric diffusion direction, and determine the leakage abnormality area; The leakage area judgment model includes a diffusion direction extension layer, a leakage range specification layer and a leakage area identification layer; The diffusion direction extension layer corrects and extends the dielectric diffusion direction according to the soil permeability parameters of the dielectric diffusion area to obtain diffusion direction data; The leakage range specification layer obtains diffusion direction intersection points based on diffusion direction data of urban sub-regions, determines the leakage range based on pipe network distribution data, and uses diffusion direction intersection points within the leakage range as candidate leakage points; According to the correlation influence coefficient of the diffusion direction data associated with the candidate leakage point, the candidate influence weight is calculated; The leakage area identification layer performs cluster analysis based on the selected leakage points and the selected influence weights to obtain the leakage area; The leakage warning module identifies leakage anomaly areas, correlation influence coefficients, and dielectric feedback data to obtain pipeline network leakage parameters; and calculates warning coefficients based on pipeline network leakage parameters. The dynamic prediction module predicts based on the dielectric feedback data and the pipeline leakage parameters to obtain the dielectric prediction parameters; based on the dielectric prediction parameters, the warning coefficient is corrected and an early warning is issued.

2. The urban underground pipeline network multi-scale deformation simulation and risk prediction cloud platform according to claim 1 is characterized by: The dielectric diffusion direction identification process is as follows: obtaining dielectric feedback data of urban sub-areas, where the dielectric feedback data is time series data; identifying the variation characteristics of the dielectric feedback data, and fitting to obtain the dielectric diffusion direction.

3. The urban underground pipe network multi-scale deformation simulation and risk prediction cloud platform according to claim 1 is characterized by: The calculation process of the early warning coefficient is as follows: A leakage anomaly simulation model is constructed to identify leakage anomaly areas, associated influence coefficients, and dielectric feedback data to obtain pipeline network leakage data, which includes leakage direction and leakage flow. An early warning coefficient is obtained based on the leakage direction and leakage flow.

4. The urban underground pipeline network multi-scale deformation simulation and risk prediction cloud platform according to claim 1 is characterized by: The correction process of the warning coefficient is as follows: Make predictions based on dielectric feedback data and pipe network leakage parameters to obtain dielectric prediction parameters; The actual dielectric data is obtained from satellite detection, and the actual variation coefficient is obtained based on the actual dielectric data and dielectric prediction parameter identification; The early warning correction factor is calculated based on the actual change coefficient and correlation influence coefficient of the urban sub-region; The warning coefficient is corrected according to the warning correction factor.

Images