Smart City Lifeline Engineering Emergency Supervision Method and Internet of Things Large Model System

Abstract

The present invention provides an emergency supervision method for a smart city lifeline project and an Internet of Things large model system, which relate to the field of emergency supervision technology. The Internet of Things large model system includes an emergency supervision user platform, an emergency supervision service platform, an emergency supervision management platform, an emergency supervision sensor network platform, and an emergency supervision object platform. The method is executed by the emergency supervision management platform, and includes: in response to the gas environment characteristics corresponding to the target pipeline meeting the early warning conditions, every preset period: based on the spatial connectivity information corresponding to the target pipeline, determining the target sensor and obtaining the corresponding air flow data; based on the gas transportation data, spatial connectivity information, air flow data and regional soil characteristics of the target pipeline, determining the estimated diffusion amplitude of the target gas; based on the estimated diffusion amplitude, determining the inspection frequency and sampling frequency to obtain soil samples during the inspection; and receiving leakage warnings. The present invention can achieve accurate identification of leakage risks and timely warnings.

Description

Technical Field

[0001] The present invention relates to the field of emergency supervision technology, and in particular to a smart city lifeline project emergency supervision method and an Internet of Things large model system. Background Art

[0002] The management of various pipelines, including gas pipelines, is a critical component of urban lifeline projects. Because many pipelines are located underground, toxic, hazardous, or flammable and explosive gases, such as natural gas, hydrogen sulfide, coal gas, and chlorine, can spread through small leaks into surrounding underground trenches and even seep into the soil, posing potential health risks to residents or serious safety accidents. Currently, robotic inspections primarily focus on detecting pipeline leaks, but monitoring gases in the soil or trenches is relatively neglected. Assessing the extent of gas diffusion in different pipelines and surrounding soil to implement targeted prevention and control measures in different areas is a critical issue.

[0003] Therefore, it is necessary to provide an emergency supervision method for smart city lifeline projects, which can adjust the working parameters of the inspection robot in real time according to the actual situation of gas diffusion around the pipeline, so as to achieve accurate identification of leakage risks and timely warnings, and realize effective emergency supervision. Summary of the Invention

[0004] In order to solve the problem of how to evaluate the diffusion range of leaked gas in different pipelines and surrounding soil, the present invention provides an emergency supervision method for smart city lifeline projects and an Internet of Things large model system.

[0005] The invention content includes a method for emergency supervision of smart city lifeline projects, which includes: in response to the gas environment characteristics corresponding to the target pipeline meeting the early warning conditions, every preset period: based on the spatial connectivity information corresponding to the target pipeline, determining the target sensor, and obtaining the air flow data corresponding to the target sensor; obtaining the regional soil characteristics corresponding to the target pipeline; based on the gas transport data of the target pipeline, the spatial connectivity information, the air flow data and the regional soil characteristics, determining the estimated diffusion amplitude of the target gas; based on the estimated diffusion amplitude, determining the inspection frequency and the sampling frequency, and sending them to the emergency supervision object platform to control the inspection robot to conduct inspections based on the inspection frequency, and sampling the soil based on the sampling frequency during the inspection to obtain soil samples; and receiving a leakage warning sent by the inspection robot when the soil sample is in an abnormal state.

[0006] The invention content includes an Internet of Things large-scale model system for emergency supervision of smart city lifeline projects. The Internet of Things large-scale model system includes an emergency supervision user platform, an emergency supervision service platform, an emergency supervision management platform, an emergency supervision sensor network platform, and an emergency supervision object platform; the emergency supervision management platform is configured to execute a smart city lifeline project emergency supervision method.

[0007] The beneficial effects brought about by the above invention include but are not limited to: (1) the inspection frequency and sampling frequency of the inspection robot are controlled based on the estimated diffusion amplitude, and the working parameters of the inspection robot can be adjusted in real time according to the actual situation of gas diffusion around the pipeline, so as to achieve accurate judgment of leakage risk and timely warning, realize effective emergency supervision, and reduce the hazards of gas leakage; (2) based on the diffusion amplitude of the target gas corresponding to the connection position, the estimated diffusion amplitude is adjusted, which can improve the accuracy of the estimated diffusion amplitude; (3) based on the first diffusion amplitude of the diffusion stage, the display frequency and display color of the positioning component are dynamically generated, which can dynamically respond to diffusion changes and realize risk visualization and graded warning; (4) by determining the placement point of the positioning component and the suction power and suction period of the negative pressure suction device, it is possible to achieve accurate positioning of the gas leakage risk, dynamic graded response and automated emergency disposal, thereby quickly suppressing gas diffusion, optimizing resource allocation, and reducing the risk of casualties and environmental pollution. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The present invention will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0009] Figure 1 1 is a system structure diagram of a large-scale model system for emergency supervision of an Internet of Things for a smart city lifeline project according to some embodiments of the present invention;

[0010] Figure 2 is an exemplary flow chart of a method for emergency supervision of a smart city lifeline project according to some embodiments of the present invention;

[0011] Figure 3 is an exemplary schematic diagram of determining a first diffusion amplitude according to some embodiments of the present invention;

[0012] Figure 4 is an exemplary flow chart of determining an estimated diffusion amplitude according to some embodiments of the present invention;

[0013] Figure 5 is an exemplary schematic diagram of determining the second diffusion amplitude according to some embodiments of the present invention. DETAILED DESCRIPTION

[0014] The following is a brief introduction to the drawings used in the description of the embodiments, which do not represent all embodiments.

[0015] When operations are described in steps in the embodiments of the invention, unless otherwise specified, the order of the steps is interchangeable, steps may be omitted, and other steps may be included in the operation process.

[0016] Figure 1 1 is a system structure diagram of a large-scale model system of the Internet of Things for emergency supervision of smart city lifeline projects according to some embodiments of the present invention.

[0017] In some embodiments, as Figure 1 As shown, the smart city lifeline project emergency supervision Internet of Things large model system 100 includes an emergency supervision user platform 110, an emergency supervision service platform 120, an emergency supervision management platform 130, an emergency supervision sensor network platform 140 and an emergency supervision object platform 150.

[0018] The emergency supervision user platform refers to a platform for initiating emergency supervision needs and receiving emergency supervision feedback information, and can be configured as a user terminal, such as a computer or other device with input and / or output functions.

[0019] The emergency supervision service platform refers to an interactive service platform for receiving and transmitting data, which may include communication terminals, such as wireless phones, video monitors, multimedia computers, etc.

[0020] In some embodiments, the emergency supervision service platform 120 interacts with the emergency supervision user platform 110 upwards and interacts with the emergency supervision management platform 130 downwards.

[0021] The emergency supervision management platform refers to a comprehensive platform for processing and managing emergency supervision data, which may include processors and storage devices, etc.

[0022] In some embodiments, the emergency supervision management platform 130 is configured to execute a smart city lifeline project emergency supervision method. For more information about this method, see Figure 2-Figure 5 Related description.

[0023] The emergency supervision sensor network platform refers to a management platform for transmitting emergency supervision related sensor data or information, which may include communication networks or gateways and network interfaces, etc.

[0024] In some embodiments, the emergency supervision sensor network platform 140 may interact with the emergency supervision management platform 130 upwards and with the emergency supervision object platform 150 downwards.

[0025] Emergency supervision platform 150 is a platform for collecting emergency supervision data and implementing execution instructions, and includes inspection robots. In some embodiments, the inspection robots in emergency supervision platform 150 are configured to conduct inspections based on an inspection frequency, sample soil based on a sampling frequency during inspections, and transmit leak warnings to the emergency supervision management platform when the soil samples are abnormal.

[0026] In some embodiments of the present invention, the IoT large-scale model system for emergency supervision of smart city lifeline projects can form an information operation closed loop between various functional platforms, and operate in a coordinated and regular manner under the unified management of the emergency supervision management platform, thereby improving the efficiency of handling emergency scenarios by dynamically adjusting the inspection frequency and sampling frequency of the inspection robot efficiently and accurately.

[0027] Figure 2 is an exemplary flow chart of a method for emergency supervision of a smart city lifeline project according to some embodiments of the present invention. In some embodiments, the process of the method for emergency supervision of a smart city lifeline project can be executed by an emergency supervision management platform, such as Figure 2 As shown, the process of the emergency supervision method for smart city lifeline projects includes: in response to the gas environment characteristics corresponding to the target pipeline meeting the warning conditions, the emergency supervision management platform executes the following steps S210 to S250 every preset period.

[0028] The target pipeline refers to the pipeline that needs to be monitored for gas leakage.

[0029] Gas environment characteristics refer to characteristics related to the gas in the target area where the target pipeline is located. Examples include the concentration of the target gas in the soil of the target area, the air velocity in the target area, etc. The target area refers to the area within a first preset range around the target pipeline. The first preset range can be manually preset based on experience.

[0030] In some embodiments, the gas environment characteristics corresponding to the target pipeline can be monitored by the inspection robot and uploaded to the emergency supervision and management platform in real time.

[0031] The target gas is the gas currently being transported in the target pipeline and can be represented by its primary component. For example, if the target pipeline is transporting natural gas, the corresponding target gas is methane.

[0032] Warning conditions are those that trigger emergency inspections. These conditions can include the concentration of the target gas in the soil of the target area exceeding a corresponding first concentration threshold and / or the air flow rate exceeding a reference velocity range. If the gas environment characteristics corresponding to the target pipeline meet these warning conditions, indicating a high probability of a gas leak, the inspection robot will be controlled to conduct enhanced inspections to further determine the location of the leak.

[0033] In some embodiments, the first concentration threshold and the reference flow rate range corresponding to the target gas can be manually preset.

[0034] In some embodiments, the preset period can be set manually based on historical experience or historical data, for example, 5 minutes, 10 minutes, etc.

[0035] Step S210 : determining a target sensor based on the spatial connectivity information corresponding to the target pipe, and acquiring air flow data corresponding to the target sensor.

[0036] Spatial connectivity information refers to information related to the spatial connectivity of the target pipeline within the target area. For example, the connectivity relationship between the target pipeline and underground pipe corridors, trenches, and manholes within the target area, including the connection direction and the coordinates of the connection location.

[0037] In some embodiments, the emergency supervision management platform can obtain spatial connectivity information corresponding to the target pipeline based on a pre-stored underground pipeline completion drawing.

[0038] In some embodiments, the emergency supervision and management platform can determine target sensors by using sensors deployed in underground pipe corridors, trenches, manholes, etc. within the target area. Types of target sensors include thermal anemometers, vane anemometers, etc.

[0039] The air flow data corresponding to the target sensor includes the air flow speed and air flow direction collected by the target sensor.

[0040] Step S220: Acquire regional soil characteristics corresponding to the target pipeline.

[0041] Regional soil characteristics include soil characteristics at multiple points in the target area. Soil characteristics include soil density, soil porosity, soil moisture content, etc.

[0042] In some embodiments, for a location, the emergency supervision and management platform can determine the average of the soil characteristics obtained from the most recent M soil samplings at that location as the soil characteristic for that location. The sequence of soil characteristics from multiple locations in the target area is the regional soil characteristic. The most recent M soil samplings refer to the M historical soil samplings most recent to the current moment. M can be manually selected based on actual circumstances, for example, 3, 5, etc.

[0043] The inspection robot is equipped with a sampling device (such as a robotic arm) and multiple types of sensors (such as soil moisture sensors, density sensors, etc.) to take soil samples and analyze soil characteristics, and upload them to the emergency supervision and management platform.

[0044] In some embodiments, the emergency supervision and management platform may evenly divide the target area into multiple points. For example, the target area may be divided into multiple sub-areas of equal area, with the center point of each sub-area being a point.

[0045] Step S230 , determining an estimated diffusion range of the target gas based on the gas transport data, spatial connectivity information, air flow data, and regional soil characteristics of the target pipeline.

[0046] The gas transport data may include the type, flow rate, transport pressure, etc. of the target gas transported by the target pipeline, and may be detected and acquired by sensors (eg, component detectors, flow meters, pressure sensors, etc.) arranged in the target pipeline.

[0047] The estimated diffusion amplitude may include the estimated diffusion range, estimated diffusion speed, and estimated diffusion amount of the target gas.

[0048] The diffusion range can be expressed by the area of ​​the target gas diffusion. The diffusion rate can be expressed by the area diffused per unit time. The diffusion amount can be expressed by the leakage amount of the target gas.

[0049] In some embodiments, the emergency supervision and management platform can determine the estimated diffusion range by querying a first preset table based on gas transportation data, spatial connectivity information, air flow data, and regional soil characteristics.

[0050] The first preset table includes a correspondence between gas transport data, spatial connectivity information, air flow data, regional soil characteristics, and estimated diffusion ranges. The first preset table can be manually constructed based on historical data. For example, the first preset table can be constructed using historical gas transport data, spatial connectivity information, air flow data, and regional soil characteristics recorded during multiple historical monitoring sessions, and the corresponding historical actual diffusion ranges.

[0051] In some embodiments, the estimated diffusion range includes the first diffusion range corresponding to the diffusion stage. The emergency supervision management platform can determine the first diffusion range by dividing the model. For more information about this part, see Figure 3 And related instructions.

[0052] In some embodiments, the emergency supervision and management platform can determine the second diffusion amplitude corresponding to the connected location based on gas transportation data, spatial connectivity information, air flow data, connectivity characteristics corresponding to the connected location, and location soil characteristics. Figure 4 And related instructions.

[0053] In step S240, based on the estimated diffusion amplitude, the inspection frequency and sampling frequency are determined and sent to the emergency supervision object platform to control the inspection robot to conduct inspections based on the inspection frequency, and to sample the soil based on the sampling frequency during the inspection to obtain soil samples.

[0054] Inspection frequency refers to the number of inspections the inspection robot performs per unit time, such as 10 times per hour. Sampling frequency refers to the number of soil samples the inspection robot takes during a single inspection.

[0055] In some embodiments, the emergency supervision management platform may determine the inspection frequency and sampling frequency by querying a second preset table based on the estimated diffusion range.

[0056] The second preset table includes the correspondence between the estimated diffusion amplitude and the inspection frequency and the sampling frequency. The second preset table can be constructed manually based on historical experience or historical data.

[0057] Step S250: receiving a leakage warning sent by the inspection robot when the soil sample is in an abnormal state.

[0058] In some embodiments, in response to the concentration of the target gas in soil samples at N consecutive locations exceeding a first concentration threshold, the inspection robot determines that the soil samples are in an abnormal state, generates a leak warning, and transmits it to the emergency supervision and management platform. The "N consecutive locations" may refer to the N locations at which the inspection robot continuously performs soil sampling. The value of N and the first concentration threshold may be manually set based on historical experience.

[0059] The leak warning is used to alert the user that a gas leak may occur in the target pipeline. The leak warning includes the gas leak point and the concentration of the target gas in the corresponding soil sample. The gas leak point refers to the point where the gas leak occurs in the pipeline. In some embodiments, there are multiple pipeline preset points on the target pipeline, and the pipeline preset points can be pre-calibrated manually. The emergency supervision management platform can determine the point with the highest concentration of the target gas among N consecutive points where the soil sample is in an abnormal state, and determine the pipeline preset point closest to it as the gas leak point.

[0060] Some embodiments of the present invention control the inspection frequency and sampling frequency of the inspection robot based on the estimated diffusion amplitude. They can adjust the working parameters of the inspection robot in real time according to the actual situation of gas diffusion around the pipeline, so as to achieve accurate identification of leakage risks and timely warnings, realize effective emergency supervision, and reduce the hazards of gas leakage.

[0061] Figure 3 is an exemplary schematic diagram of determining a first diffusion amplitude according to some embodiments of the present invention.

[0062] In some embodiments, the estimated diffusion amplitude includes a first diffusion amplitude corresponding to the diffusion stage.

[0063] For more information on estimating the magnitude of the spread, see Figure 2 And related instructions.

[0064] Diffusion stages refer to the different stages of a target gas's diffusion through the soil. For example, the emergency monitoring and management platform can use the gas leak point as the center and divide the area into multiple concentric circles with preset radii of different distances. These circles, arranged from the innermost ring to the outermost ring, represent diffusion ranges. The process from the target gas entering a diffusion range until it fills the diffusion range is recorded as the diffusion stage corresponding to that diffusion range. In other words, each diffusion range corresponds to a diffusion stage, and each diffusion stage has its own corresponding diffusion speed and diffusion volume.

[0065] The first diffusion amplitude refers to the diffusion amplitude of the target gas during each diffusion stage. The diffusion period, diffusion range, diffusion speed, and diffusion amount corresponding to each diffusion stage constitute the first diffusion amplitude corresponding to that diffusion stage. The estimated diffusion amplitude includes the first diffusion amplitudes corresponding to multiple diffusion stages.

[0066] The diffusion period corresponding to the diffusion stage refers to the time period from when the target gas diffuses into the diffusion range corresponding to the diffusion stage to when the target gas diffuses throughout the diffusion range.

[0067] In some embodiments, as Figure 3 As shown, the emergency supervision and management platform can determine the first diffusion amplitude 370 corresponding to the diffusion stage through a division model 350 based on gas transportation data 310, spatial connectivity information 320, air flow data 330 and regional soil characteristics 340; and adjust the first diffusion amplitude 370 based on the density difference 360 ​​between the target gas and the air.

[0068] The partitioning model is a model used to determine the first diffusion amplitude. In some embodiments, the partitioning model is a machine learning model, such as a deep neural network (DNN) model.

[0069] The input of the partitioning model includes gas transport data, spatial connectivity information, air flow data and regional soil characteristics, and the output of the partitioning model includes the first diffusion amplitude corresponding to the diffusion stage.

[0070] For more information on gas transport data, spatial connectivity information, air flow data, and regional soil characteristics, see Figure 2 And related instructions.

[0071] In some embodiments, the emergency supervision management platform can train a partitioning model based on multiple first training samples with first labels. The emergency supervision management platform can input the first training sample into the initial partitioning model, construct a loss function based on the first label and the output of the initial partitioning model, iteratively update the parameters of the initial partitioning model based on the loss function, and terminate the iteration when the iteration end condition is met to obtain a trained partitioning model. The iterative update method includes but is not limited to the gradient descent method, and the iteration end condition can be that the loss function converges or the number of iterations reaches a threshold.

[0072] The first training sample can be obtained based on historical data. The first training sample includes historical gas transportation data corresponding to the historical target pipeline, historical spatial connectivity information, historical air flow data, and historical regional soil characteristics.

[0073] The first tag includes a reference first diffusion amplitude corresponding to a historical target pipeline in a plurality of reference diffusion stages.

[0074] A historical target pipeline corresponding to a first training sample has multiple historical leakage processes, and each historical leakage process has a corresponding historical gas leakage point.

[0075] For each historical gas leakage point, the emergency supervision and management platform can construct multiple clustering vectors based on the historical diffusion range, historical diffusion period, historical diffusion speed and historical diffusion amount corresponding to the historical gas leakage point in multiple historical leakage processes. A clustering vector is composed of the historical diffusion range, historical diffusion period, historical diffusion speed and historical diffusion amount corresponding to a historical leakage process; multiple clustering vectors are clustered based on the historical diffusion speed and historical diffusion amount to obtain multiple cluster clusters.

[0076] For each cluster, the average value of the historical diffusion ranges corresponding to the multiple cluster vectors in the cluster is determined as a reference diffusion range, that is, a reference diffusion stage is determined, the union of the historical diffusion time periods corresponding to the multiple cluster vectors in the cluster is determined as the reference diffusion time period corresponding to the reference diffusion stage, and the mean value of the historical diffusion speed and the mean value of the historical diffusion amount corresponding to the multiple cluster vectors in the cluster are respectively determined as the reference diffusion speed and reference diffusion amount corresponding to the reference diffusion stage.

[0077] Multiple clusters are obtained to obtain multiple reference diffusion stages and corresponding multiple reference diffusion ranges, multiple reference diffusion speeds and multiple reference diffusion amounts, and multiple reference first diffusion amplitudes corresponding to the multiple reference diffusion stages can be constructed as first labels.

[0078] Clustering methods include but are not limited to K-Means clustering algorithm, DBSCAN clustering algorithm, etc.

[0079] In some embodiments, the emergency supervision management platform can directly obtain the density of the target gas and the air density that are manually uploaded in advance, and determine the absolute value of the difference between the two as the density difference between the target gas and the air.

[0080] In some embodiments, the emergency supervision management platform may determine the diffusion velocity influence value and the diffusion amount influence value by querying a third preset table based on the density difference between the target gas and the air.

[0081] The third preset table includes a correspondence between the density difference between the target gas and air, the diffusion velocity impact value, and the diffusion volume impact value. A greater density difference between the target gas and air indicates a greater diffusion velocity impact value and a greater diffusion volume impact value. The third preset table can be constructed manually based on historical experience.

[0082] The diffusion velocity influence value and the diffusion amount influence value respectively reflect the density difference between the target gas and air, and the degree of influence on the diffusion velocity and diffusion amount of the target gas.

[0083] In some embodiments, the emergency supervision management platform may determine the product of the diffusion speed and the diffusion speed influence value as the adjusted diffusion speed, and determine the product of the diffusion amount and the diffusion amount influence value as the adjusted diffusion amount, thereby obtaining the adjusted first diffusion amplitude.

[0084] The density difference between the target gas and air significantly affects the target gas's permeability resistance in soil, thereby affecting the target gas's diffusion rate and volume. In some embodiments of the present invention, adjusting the first diffusion amplitude based on the density difference between the target gas and air can improve the reliability of the predicted diffusion amplitude.

[0085] Figure 4 FIG. 1 is an exemplary flow chart of determining the estimated diffusion amplitude according to some other embodiments of the present invention. Figure 4 As shown, the process of determining the estimated spread range includes the following steps S410 to S430. In some embodiments, the process of determining the estimated spread range can be executed by the emergency supervision management platform.

[0086] Step S410: determining the location soil characteristics corresponding to the connected locations based on the spatial connectivity information and the regional soil characteristics.

[0087] For more information on estimating dispersal amplitudes, spatial connectivity information, and regional soil characteristics, see Figure 2 And related instructions.

[0088] The location soil characteristics refer to the soil characteristics corresponding to the connected location. In some embodiments, the emergency supervision and management platform can determine the soil characteristics of the point closest to the connected location as the location soil characteristics corresponding to the connected location.

[0089] In some embodiments, the emergency supervision management platform can determine a preset number of neighboring points of the connected location and the location soil characteristics corresponding to the neighboring points based on spatial connectivity information and regional soil characteristics; and determine the location soil characteristics corresponding to the connected location based on the location soil characteristics corresponding to the neighboring points.

[0090] In some embodiments, the preset number is related to soil characteristics of the area corresponding to the target pipeline. A larger standard deviation or variance of soil characteristics at multiple points in the target area indicates a more complex distribution of soil composition and type in the target area. Therefore, a larger preset number is required to improve the reliability of the soil characteristics at that location.

[0091] In some embodiments, the emergency supervision management platform can determine a preset number of points closest to the connected location as neighboring points, and determine the average value of the soil characteristics corresponding to the preset number of neighboring points as the location soil characteristics corresponding to the connected location.

[0092] In some embodiments of the present invention, the soil characteristics of the location corresponding to the connected location are determined based on the soil characteristics of multiple points near the connected location, and the obtained location soil characteristics are more accurate.

[0093] Step S420 , determining a second diffusion amplitude corresponding to the connected position based on the gas transport data, the spatial connectivity information, the air flow data, the connectivity characteristics corresponding to the connected position, and the soil characteristics of the position.

[0094] Connectivity characteristics refer to characteristics related to the connectivity of a connected location. For example, connectivity characteristics include whether the connection point has an opening or direct contact with the soil. Connectivity characteristics corresponding to a connected location can also be determined based on as-built drawings of underground pipelines.

[0095] The second diffusion amplitude refers to the diffusion amplitude of the target gas at the communication position. For example, the second diffusion amplitude includes an estimated diffusion range, an estimated diffusion speed, an estimated diffusion amount, etc. of the target gas at the communication position.

[0096] In some embodiments, the emergency supervision and management platform can determine the second diffusion amplitude by querying a fourth preset table based on gas transport data, spatial connectivity information, air flow data, connectivity characteristics corresponding to the connected location, and location soil characteristics.

[0097] The fourth preset table includes a correspondence between gas transport data, spatial connectivity information, air flow data, connectivity characteristics corresponding to connected locations, soil characteristics at those locations, and the second diffusion amplitude. The fourth preset table can be manually constructed based on historical data. For example, the fourth preset table can be constructed using historical gas transport data, historical spatial connectivity information, historical air flow data, historical connectivity characteristics corresponding to connected locations, and historical soil characteristics at those locations, recorded during multiple historical monitoring sessions, along with the corresponding historical actual second diffusion amplitudes.

[0098] In some embodiments, the emergency supervision and management platform can construct a gas circulation map based on gas transportation data, spatial connectivity information, air flow data, connectivity characteristics corresponding to the connected locations, and location soil characteristics; based on the gas circulation map, the second diffusion amplitude corresponding to the connected locations can be determined through a prediction model. Figure 5 And related instructions.

[0099] Step S430: adjusting the estimated diffusion amplitude based on the second diffusion amplitude.

[0100] In some embodiments, the emergency supervision management platform may determine the estimated diffusion range corresponding to the estimated diffusion amplitude determined by querying the first preset table and the overlapping portion of the estimated diffusion range corresponding to the second diffusion amplitude as the adjusted diffusion range; perform a weighted sum of the estimated diffusion speed corresponding to the estimated diffusion amplitude determined by querying the first preset table and the estimated diffusion speed corresponding to the second diffusion amplitude, and determine the weighted sum result as the adjusted diffusion amplitude, with the weight of the estimated diffusion speed corresponding to the estimated diffusion amplitude being much greater than the weight of the estimated diffusion speed corresponding to the second diffusion amplitude. The method for adjusting the diffusion amount is similar and will not be elaborated here, and the adjusted estimated diffusion amplitude can be obtained.

[0101] In some embodiments of the present invention, the estimated diffusion amplitude is adjusted based on the diffusion amplitude of the target gas corresponding to the connection position, which can improve the accuracy of the estimated diffusion amplitude.

[0102] Figure 5 is an exemplary schematic diagram of determining the second diffusion amplitude according to some embodiments of the present invention.

[0103] In some embodiments, as Figure 5 As shown, the emergency supervision and management platform can construct a gas circulation map 530 based on gas transport data 310, spatial connectivity information 320, air flow data 330, connectivity characteristics 510 corresponding to the connected position, and location soil characteristics 520; based on the gas circulation map 530, the second diffusion amplitude 550 corresponding to the connected position is determined through the prediction model 540.

[0104] A gas flow graph is a graph that describes the flow path and characteristics of the target gas and consists of nodes and directed edges.

[0105] In some embodiments, the nodes of the gas flow map include connection locations and gas leakage points.

[0106] The node features corresponding to the connected positions may include the connectivity features of the connected positions and the soil features of the positions.

[0107] The node features corresponding to the gas leakage point may include gas transportation data.

[0108] For more information on gas transport data, connectivity locations, connectivity characteristics, and location soil characteristics, see Figure 2 and Figure 4 Related instructions.

[0109] In some embodiments, for any node in the gas flow map, the node feature of the node further includes a standard deviation of location soil features of a plurality of points within a preset range corresponding to the node.

[0110] In some embodiments, the preset range corresponding to the node may refer to a range area at a preset distance from the node. The preset distance may be manually preset. The preset range may be smaller than the first preset range described above.

[0111] In some embodiments of the present invention, the standard deviation of the location soil characteristics of multiple points within a preset range corresponding to the node is used as the node feature, which can more accurately reflect the local complexity of the soil composition and soil structure near the node, thereby improving the accuracy of the subsequent determination of the diffusion rate of the target gas through the prediction model, and providing more reliable data support for emergency supervision decisions.

[0112] In some embodiments, the directed edges of the gas flow map include underground pipe galleries, trenches, manholes, etc. between nodes, and the direction of the edge is the direction of gas flow.

[0113] Edge features include air flow data from target sensors in underground pipe corridors, trenches, manholes, etc. For more information about air flow data, see Figure 2 Related instructions.

[0114] The prediction model is used to predict the second diffusion amplitude. In some embodiments, the prediction model may be a machine learning model, such as a Graph Neural Network (GNN) model. In some embodiments, the prediction model input may include a gas flow map, and the output may include the second diffusion amplitude corresponding to the connected location.

[0115] In some embodiments, the prediction model can be trained based on a large number of second training samples with second labels. The second training samples can be obtained based on historical data. The second training samples can include historical gas flow maps corresponding to historical target pipelines, and the second labels can be historical actual second diffusion amplitudes corresponding to each historical connection location.

[0116] In some embodiments, a historical target pipeline corresponding to a second training sample has multiple historical leakage processes, and each historical leakage process has a corresponding historical gas flow map. For each historical connection position, the average of the historical actual second diffusion amplitudes of the historical connection position in the multiple historical gas flow maps is calculated and determined as the historical actual second diffusion amplitude of the historical connection position, and the second label can be obtained. The historical actual second diffusion amplitude is obtained from the historical inspection record data and manually marked as the second label. The training process of the prediction model can be seen in Figure 3 The training process of the partitioning model is not described here.

[0117] In some embodiments of the present invention, by constructing a gas flow map and determining the second diffusion amplitude corresponding to the connected position based on a prediction model, and by integrating multi-dimensional dynamic data such as gas transport data, connectivity characteristics, and soil characteristics, the risk of target gas diffusion can be more accurately assessed, and it can also adapt to different pipeline network topologies and leakage scenarios, thereby optimizing inspection and emergency management and improving the safety of urban lifeline projects.

[0118] In some embodiments, in response to a gas leak in a target pipeline, the emergency supervision management platform can determine a target point where the gas concentration in the soil is greater than a preset concentration threshold based on the inspection data of the inspection robot, and / or determine a target connection position where the diffusion amount is greater than a preset diffusion threshold based on the second diffusion amplitude corresponding to the connection position, and determine the target point and / or target connection position as the placement point of the positioning component; based on the air flow data, generate the suction power and suction time period of the negative pressure suction device; send the placement point, suction power and suction time period to the emergency supervision object platform to control the inspection robot to place the positioning component at the placement point, and control the negative pressure suction device to pump and / or inhale air based on the suction power and suction time period.

[0119] In some embodiments, after receiving a leak warning from the inspection robot, the emergency monitoring and management platform can determine whether the pressure in the target pipeline is less than a pressure threshold. If the pressure in the target pipeline is less than the pressure threshold, a gas leak is determined to have occurred in the target pipeline. The pressure threshold can be manually preset based on prior experience or set by system default. The pressure of the target pipeline can be detected and acquired by a pressure sensor deployed within the pipeline and uploaded to the emergency monitoring and management platform.

[0120] Inspection data refers to data collected by the inspection robot during the inspection process. For example, the inspection data may include the concentration of target gases in soil samples at various locations. In some embodiments, the inspection data may be uploaded by the inspection robot to the emergency supervision and management platform.

[0121] Target points refer to points that require focused monitoring and / or processing during the inspection process. In some embodiments, the emergency supervision and management platform can determine points where the concentration of the target gas in the soil sample is greater than a preset concentration threshold as target points.

[0122] A target connection location refers to a connection location that requires focused monitoring and / or processing. In some embodiments, the emergency supervision management platform may determine, based on the first diffusion amplitude corresponding to the connection location, a connection location with a diffusion amount greater than a preset diffusion threshold as a target connection location.

[0123] In some embodiments, the preset concentration threshold and the preset diffusion threshold can be manually preset based on experience. The preset concentration threshold can be greater than the first concentration threshold.

[0124] In some embodiments, the preset concentration threshold and the preset diffusion threshold are related to crowd density and / or building density.

[0125] Crowd density refers to the number of permanent residents or people monitored in real time per unit area; building density refers to the number of buildings per unit area or the percentage of building area. In some embodiments, the inspection robot may also be equipped with an image acquisition device (e.g., a camera) to capture images and upload them to the emergency supervision and management platform. The emergency supervision and management platform can then perform image recognition on the images to determine crowd and building density. Image recognition methods may include computer vision methods, deep learning models, etc.

[0126] In some embodiments, the preset concentration threshold and the preset diffusion threshold may be negatively correlated with crowd density and / or building density. For example, a greater crowd density and / or building density indicates a greater risk of gas poisoning, and the preset concentration threshold and the preset diffusion threshold may need to be smaller.

[0127] In some embodiments of the present invention, by determining a preset concentration threshold and a preset diffusion threshold based on crowd density and / or building density, dynamic risk classification management can be achieved, thereby optimizing emergency resource allocation while ensuring public safety.

[0128] Positioning components are components used to mark areas where there is a risk of gas leakage, such as warning lights, warning signs, etc.

[0129] The placement point refers to the point where the positioning component is placed.

[0130] In some embodiments, the emergency supervision management platform may directly determine the target point and / or target connectivity position as the placement point of the positioning component.

[0131] A negative pressure suction device is a device that extracts and collects gas and / or particles by generating negative pressure, such as a negative pressure pump. Negative pressure suction devices can be deployed near the outlet of pipe trenches, underground pipe galleries, and manholes.

[0132] In some embodiments, the emergency supervision and management platform can determine whether the target gas is flowing to an area where the crowd density is greater than a crowd threshold and / or the building density is greater than a building threshold based on spatial connectivity information and air flow data. If so, multiple negative pressure suction devices arranged at the locations where the target gas flows through in underground pipe corridors, trenches, and manholes are activated, and the negative pressure suction devices are controlled to pump and / or inhale air based on the suction power and suction period, thereby changing the air flow direction and air flow rate in the underground space to ensure that the flow direction of the target gas is changed, thereby ensuring the safety of areas where people and / or buildings gather. Among them, the crowd threshold and building threshold can be preset based on prior experience.

[0133] The suction power refers to the power of the negative pressure suction device when it is working. The suction period refers to the operating period of the negative pressure suction device.

[0134] In some embodiments, the suction power is dynamically adjusted. The emergency management platform can control the negative pressure suction device to increase its power from a standard suction power until the air flow direction changes. The power of the negative pressure suction device at this point is determined as the stable suction power. The negative pressure suction device will continue to pump at the stable suction power during the suction period. The standard suction power can be preset based on prior experience.

[0135] In some embodiments, the emergency monitoring and management platform can determine the time when the target gas flows through each location based on the air flow rate; for each location, the corresponding negative pressure suction device is pre-activated within a preset period before the corresponding time until the air flow direction at that location changes and stabilizes, at which point the corresponding negative pressure suction device is turned off. The period from the time the negative pressure suction device is turned on to the time it is turned off is the suction period. The length of the preset period can be manually preset based on experience.

[0136] In some embodiments, the emergency supervision management platform can generate a display frequency and display color corresponding to the placement point based on the first diffusion amplitude corresponding to the diffusion stage, and send it to the emergency supervision object platform to control the positioning component to flash based on the display frequency and emit light based on the display color.

[0137] For more information on the diffusion phase and the first diffusion amplitude, see Figure 3 And related instructions.

[0138] In some embodiments, the emergency monitoring and management platform can obtain the diffusion stage of the positioning component based on the diffusion range of the placement point of the positioning component, and determine the display frequency and display color of the positioning component using a fifth preset table. The fifth preset table includes diffusion stages, display frequencies, and display colors. The earlier the diffusion stage, that is, the closer the diffusion range is to the gas leak point, the greater the display frequency and the more eye-catching the display color can be.

[0139] In some embodiments of the present invention, the display frequency and display color of the positioning component are dynamically generated based on the first diffusion amplitude in the diffusion stage, which can dynamically respond to diffusion changes and achieve visual risk graded warning.

[0140] In some embodiments of the present invention, by determining the placement point of the positioning component and the suction power and suction period of the negative pressure suction device, accurate positioning of gas leakage risks, dynamic graded response and automated emergency disposal can be achieved, thereby quickly suppressing gas diffusion, optimizing resource allocation, and reducing the risk of casualties and environmental pollution.

[0141] Certain features, structures or characteristics of one or more embodiments of the present invention may be appropriately combined.

[0142] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in the present invention are not intended to limit the order of the processes and methods of the present invention. Although the above disclosure discusses some embodiments of the invention that are currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of the present invention. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0143] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the referenced materials of this invention and the contents of this invention, the descriptions, definitions, and / or usage of terms in this invention shall prevail.

Claims

1. A method for emergency supervision of lifeline projects in smart cities, characterized in that: The method is executed by an emergency supervision management platform in a large-scale model system of the Internet of Things for emergency supervision of lifeline projects in a smart city, and the method includes: In response to the gas environment characteristics corresponding to the target pipeline meeting the warning conditions, every preset period: Determining a target sensor based on spatial connectivity information corresponding to the target pipe, and acquiring air flow data corresponding to the target sensor; Obtaining regional soil characteristics corresponding to the target pipeline; determining an estimated diffusion amplitude of the target gas based on the gas transport data of the target pipeline, the spatial connectivity information, the air flow data, and the regional soil characteristics; Based on the estimated diffusion amplitude, an inspection frequency and a sampling frequency are determined, and sent to the emergency supervision object platform to control the inspection robot to conduct inspections based on the inspection frequency, and to sample the soil based on the sampling frequency during the inspection to obtain soil samples; and receiving a leakage warning sent by the inspection robot when the soil sample is in an abnormal state; In response to a gas leak occurring in the target pipeline, Based on the inspection data of the inspection robot, a target point at which the gas concentration in the soil is greater than a preset concentration threshold is determined, and / or based on the second diffusion amplitude corresponding to the connection position, a target connection position at which the diffusion amount is greater than a preset diffusion threshold is determined, and the target point and / or the target connection position are determined as the placement point of the positioning component; the inspection data includes the concentration of the target gas in the soil sample; generating a suction power and a suction period of a negative pressure suction device based on the air flow data; The placement point, the suction power and the suction period are sent to the emergency supervision object platform to control the inspection robot to place the positioning component at the placement point, and control the negative pressure suction device to perform air extraction and / or inhalation based on the suction power and the suction period.

2. The method according to claim 1, wherein The estimated diffusion amplitude includes a first diffusion amplitude corresponding to the diffusion stage; and determining the estimated diffusion amplitude of the target gas based on the gas transport data of the target pipeline, the spatial connectivity information, the air flow data, and the regional soil characteristics includes: determining the first diffusion amplitude corresponding to the diffusion stage by a partitioning model based on the gas transport data, the spatial connectivity information, the air flow data, and the regional soil characteristics, wherein the partitioning model is a machine learning model; The first diffusion amplitude is adjusted based on a density difference between the target gas and air.

3. The method according to claim 1, wherein The step of determining an estimated diffusion range of the target gas based on the gas transport data of the target pipeline, the spatial connectivity information, the air flow data, and the regional soil characteristics further includes: Determining the location soil characteristics corresponding to the connected location based on the spatial connectivity information and the regional soil characteristics; determining the second diffusion amplitude corresponding to the connected location based on the gas transport data, the spatial connectivity information, the air flow data, the connectivity characteristics corresponding to the connected location, and the soil characteristics of the location; and The estimated diffusion amplitude is adjusted based on the second diffusion amplitude.

4. The method according to claim 3, wherein The determining, based on the gas transport data, the spatial connectivity information, the air flow data, the connectivity characteristics corresponding to the connectivity location, and the location soil characteristics, of the second diffusion amplitude corresponding to the connectivity location includes: constructing a gas circulation map based on the gas transport data, the spatial connectivity information, the air flow data, the connectivity features corresponding to the connectivity locations, and the soil features at the locations; Based on the gas flow map, the second diffusion amplitude corresponding to the connection position is determined by a prediction model, and the prediction model is a machine learning model.

5. A large-scale IoT model system for emergency supervision of lifeline projects in smart cities, characterized by: Including emergency supervision user platform, emergency supervision service platform, emergency supervision management platform, emergency supervision sensor network platform, and emergency supervision object platform; The emergency supervision management platform is configured to: In response to the gas environment characteristics corresponding to the target pipeline meeting the warning conditions, every preset period: Determining a target sensor based on spatial connectivity information corresponding to the target pipe, and acquiring air flow data corresponding to the target sensor; Obtaining regional soil characteristics corresponding to the target pipeline; determining an estimated diffusion amplitude of the target gas based on the gas transport data of the target pipeline, the spatial connectivity information, the air flow data, and the regional soil characteristics; Based on the estimated diffusion amplitude, an inspection frequency and a sampling frequency are determined and sent to the emergency supervision object platform; the inspection robot in the emergency supervision object platform is configured to conduct inspections based on the inspection frequency, and to sample soil based on the sampling frequency during the inspection to obtain soil samples, and to send a leakage warning to the emergency supervision management platform when the soil sample is in an abnormal state; In response to a gas leak occurring in the target pipeline, Based on the inspection data of the inspection robot, a target point at which the gas concentration in the soil is greater than a preset concentration threshold is determined, and / or based on the second diffusion amplitude corresponding to the connection position, a target connection position at which the diffusion amount is greater than a preset diffusion threshold is determined, and the target point and / or the target connection position are determined as the placement point of the positioning component; the inspection data includes the concentration of the target gas in the soil sample; generating a suction power and a suction period of a negative pressure suction device based on the air flow data; The placement point, the suction power and the suction period are sent to the emergency supervision object platform to control the inspection robot to place the positioning component at the placement point, and control the negative pressure suction device to perform air extraction and / or inhalation based on the suction power and the suction period.

6. The Internet of Things large model system according to claim 5, characterized in that: The estimated diffusion amplitude includes a first diffusion amplitude corresponding to the diffusion stage; and the emergency supervision and management platform is further configured to: determining the first diffusion amplitude corresponding to the diffusion stage by a partitioning model based on the gas transport data, the spatial connectivity information, the air flow data, and the regional soil characteristics, wherein the partitioning model is a machine learning model; The first diffusion amplitude is adjusted based on a density difference between the target gas and air.

7. The Internet of Things large model system according to claim 5, characterized in that: The emergency supervision management platform is further configured to: Determining the location soil characteristics corresponding to the connected location based on the spatial connectivity information and the regional soil characteristics; determining the second diffusion amplitude corresponding to the connected location based on the gas transport data, the spatial connectivity information, the air flow data, the connectivity characteristics corresponding to the connected location, and the soil characteristics of the location; and The estimated diffusion amplitude is adjusted based on the second diffusion amplitude.

8. The Internet of Things large model system according to claim 7, characterized in that: The emergency supervision management platform is further configured to: constructing a gas circulation map based on the gas transport data, the spatial connectivity information, the air flow data, the connectivity features corresponding to the connectivity locations, and the soil features at the locations; Based on the gas flow map, the second diffusion amplitude corresponding to the connection position is determined by a prediction model, and the prediction model is a machine learning model.

Images