Urban lifeline pipe network burst prevention system and method based on Internet of Things large model

Abstract

The invention provides an urban lifeline pipe network burst prevention system and method based on an Internet of Things large model, and the method is executed based on an emergency supervision management platform, and comprises the steps: obtaining fluid pressure data; based on the fluid pressure data, the pipe explosion probability of the pipe network node is determined; and a target valve and the valve opening degree thereof are determined based on the pipe explosion probability, and the target valve is controlled to reach the valve opening degree. The system comprises an emergency supervision management platform. According to the method, the target valve needing to be controlled can be rapidly and accurately positioned, meanwhile, the opening degree of the target valve is accurately controlled, and the influence on water consumption of urban residents is reduced while the water pipe corresponding to the pipe network node is prevented from being burst.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of urban water supply pipe network safety monitoring, in particular to a city lifeline pipe network burst prevention system and method based on an Internet of Things large model. BACKGROUND

[0002] During the operation of urban underground pipe networks, pipe burst accidents become a major safety hazard for water supply systems due to their suddenness and destructiveness. Traditional pipe burst monitoring mainly relies on pressure gauges and flow meters inside the pipe network, which monitor through a single indicator such as pressure drop, but are easily disturbed by water load fluctuations, equipment failures, and other factors, resulting in a high false positive rate. In addition, existing monitoring methods lack the ability to distinguish between pipe bursts and leaks, making it impossible to provide accurate early warnings and timely initiate appropriate emergency measures.

[0003] Therefore, it is desirable to provide a city lifeline pipe network burst prevention system and method based on an Internet of Things large model to address the shortcomings of current monitoring technologies, achieve comprehensive and real-time monitoring of urban underground pipe networks, and improve the effectiveness and timeliness of city lifeline pipe network burst prevention. SUMMARY

[0004] In order to comprehensively monitor urban underground pipe networks in real time and improve the effectiveness and timeliness of city lifeline pipe network burst prevention, the present application provides a city lifeline pipe network burst prevention system and method based on an Internet of Things large model.

[0005] The application includes a city lifeline pipe network burst prevention method based on an Internet of Things large model. The method is implemented based on a city lifeline pipe network burst prevention system based on an Internet of Things large model, and includes: obtaining fluid pressure data; determining the pipe burst probability of a pipe network node based on the fluid pressure data; and determining the target valve and its valve opening degree based on the pipe burst probability, and controlling the opening and closing of the target valve to the valve opening degree.

[0006] The application includes a city lifeline pipe network burst prevention system based on an Internet of Things large model, which includes an emergency supervision and management platform configured to execute a city lifeline pipe network burst prevention method based on an Internet of Things large model.

[0007] The technical solution of the present application analyzes the fluid pressure data in the urban water supply pipe network, determines the pipe burst probability of each pipe network node, and determines the target valve and its valve opening degree based on the pipe burst probability, which can quickly and accurately locate the target valve that needs to be controlled, and accurately control the opening degree of the target valve, avoiding the burst of the water pipe corresponding to the pipe network node while reducing the impact on urban residents' water use. BRIEF DESCRIPTION OF DRAWINGS

[0008] The present application will be further described in the way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same numbers refer to the same structures or operations, in which: Figure 1 is an exemplary structural diagram of an Internet of Things big model-based urban lifeline pipe network burst prevention system according to some embodiments of the present application; Figure 2 is an exemplary flowchart of an Internet of Things big model-based urban lifeline pipe network burst prevention method according to some embodiments of the present application; Figure 3 is an exemplary flowchart of generating a risk avoidance instruction according to some embodiments of the present application; Figure 4 is an exemplary schematic diagram of determining a pipe burst probability according to some embodiments of the present application.

[0009] Reference signs: 100-Internet of Things big model-based urban lifeline pipe network burst prevention system; 110-emergency supervision user platform; 120-emergency supervision service platform; 130-emergency supervision management platform; 140-emergency supervision sensing network platform; 150-emergency supervision object platform; 410-road surface water seepage feature; 420-fluid pressure data; 430-pipe burst prediction atlas; 440-first prediction model; 450-first pipe burst probability; 460-fluid pressure data of a preset historical period; 470-second prediction model; 480-second pipe burst probability; 490-pipe burst probability. DETAILED DESCRIPTION

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some examples or embodiments of the present application, and for those skilled in the art, the present application can be applied to other similar scenarios without creative labor. Unless it is obvious from the language environment or otherwise stated, the same reference numbers in the drawings represent the same structures or operations.

[0011] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0012] The singular forms "a," "an," and "the" do not necessarily mean the same thing, and / or "the" do not necessarily refer to the singular unless the context clearly indicates so. Generally, the terms "include," "including," and "comprise" are intended to be open-ended and not limiting.

[0013] Flowcharts are used to illustrate the operations performed by systems according to embodiments of the present application. It should be understood that the operations in the flowcharts do not necessarily have to be performed in the order shown. Rather, various steps can be performed in different orders or simultaneously. Also, other operations can be added or removed from the flowcharts.

[0014] Figure 1 is an exemplary structural diagram of an Internet-of-Things big model-based urban lifeline pipe network burst prevention system according to some embodiments of the present application.

[0015] In some embodiments, as shown in Figure 1 , the Internet-of-Things big model-based urban lifeline pipe network burst prevention system 100 can include 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.

[0016] The emergency supervision user platform 110 refers to an interactive platform for emergency management personnel and users. In some embodiments, the emergency supervision user platform 110 can include servers, gateways, display screens, etc. In some embodiments, the emergency supervision user platform 110 can be communicatively connected with user terminals (e.g., mobile phones, computers, personal digital assistants, etc.), communicate and transmit data with the user terminals based on instructions sent by the emergency supervision management platform 130, and broadcast risk avoidance instructions to the user terminals, for example. For more information about risk avoidance instructions, see Figure 3 and related descriptions.

[0017] The emergency supervision service platform 120 refers to a platform that provides emergency supervision services. In some embodiments, the emergency supervision service platform 120 can be configured as a server that performs bidirectional data interaction with the emergency supervision user platform 110 and the emergency supervision management platform 130.

[0018] The emergency supervision management platform 130 refers to a platform for supervising or managing information related to urban underground pipe networks. In some embodiments, the emergency supervision management platform 130 can include a processor, a server, a data storage system, a large screen display system, an Internet of Things platform software, a communication component (e.g., a communication interface, a gateway), etc. In some embodiments, the emergency supervision management platform 130 can be a software platform running on a server or in the cloud, for processing data and / or information obtained from other platforms (e.g., the emergency supervision service platform 120, the emergency supervision sensor network platform 140). The emergency supervision management platform 130 can execute program instructions based on the obtained data, information, and / or corresponding processing results, to perform the functions and / or steps described in the present application.

[0019] In some embodiments, the emergency supervision management platform 130 is configured to: obtain fluid pressure data; determine a pipe burst probability of a pipe network node based on the fluid pressure data; and determine a target valve and a valve opening degree of the target valve based on the pipe burst probability, and control the target valve to open or close to the valve opening degree.

[0020] In some embodiments, the emergency supervision management platform 130 can be configured in a processor and / or a server. The processor and / or the server can process data and / or information obtained from other platforms. The processor and / or the server can execute program instructions based on the data, information, and / or processing results, to perform one or more functions described in the present application. In some embodiments, the processor and / or the server can include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction processor (ASIP), etc., or any combination thereof. In some embodiments, the emergency supervision management platform 130 can include a water supply pipeline emergency supervision module and an emergency supervision data center. The water supply pipeline emergency supervision module can include a data processing model library.

[0021] The water supply pipeline emergency supervision module refers to a module for real-time monitoring, early warning, and disposal of urban underground water supply pipelines in emergency situations.

[0022] The data processing model library is used to store trained data processing large models. In some embodiments, the data processing model library can include a first prediction model, a second prediction model, etc. For more information about the first prediction model and the second prediction model, please refer to Figure 4 and related descriptions.

[0023] The emergency supervision data center refers to a platform for collecting and storing data related to urban pipe networks, such as fluid pressure data, road surface seepage characteristics, etc. In some embodiments, the emergency supervision data center can include MySQL, PostgreSQL, InfluxDB, Prometheus, etc. In some embodiments, the water supply pipeline emergency supervision module can interact with the emergency supervision data center for bidirectional data exchange.

[0024] The emergency supervision sensor network platform 140 refers to a platform for comprehensive management of sensor information. In some embodiments, the emergency supervision sensor network platform can interact with the emergency supervision management platform and the emergency supervision object platform. In some embodiments, the emergency supervision sensor network platform 140 can include communication devices, servers, and various gateway devices, etc.

[0025] The emergency supervision object platform 150 refers to a platform for various entities or systems under supervision, for displaying, managing and analyzing the operating conditions and data of the supervised objects. In some embodiments, the emergency supervision object platform can include various monitoring devices, sensors and interactive devices. For example, cameras, pressure sensors, environmental monitoring sensors, smart water meters, acoustic leak detectors, etc.

[0026] In some embodiments, the emergency supervision object platform can include a pipe network object platform. The pipe network object platform refers to a platform for collecting underground pipe network data and / or information. In some embodiments, the pipe network object platform can include water pipes, valves, pump stations, pressure regulating stations, etc.

[0027] In some embodiments, the city lifeline pipe network burst prevention system based on the Internet of Things large model 100 further includes a memory, etc. The memory is configured to store information and / or data related to the city lifeline pipe network burst prevention system based on the Internet of Things large model 100.

[0028] For more details about the city lifeline pipe network burst prevention system based on the Internet of Things large model 100, see Figures 2-4 and related descriptions.

[0029] In some embodiments of the present application, the underground pipe network of the city is supervised by the Internet of Things large model system, which can realize the monitoring and rapid response of the pipe burst of the underground pipe network, determine the pipe burst probability through intelligent analysis of the monitoring data, and generate a risk avoidance prompt on the vehicle terminal in the region, which can timely eliminate safety hazards and effectively improve the safety and reliability of the underground pipe network. At the same time, combined with automatic valve control and operation, the manpower inspection investment is reduced, and the management cost is reduced.

[0030] Figure 2 is an exemplary flowchart of the city lifeline pipe network burst prevention based on the Internet of Things large model according to some embodiments of the present application. As shown inFigure 2 As shown, the flow 200 includes the following steps. In some embodiments, the flow 200 can be performed by an emergency regulatory management platform or a processor, and the following is taken as an example of the processor performing the flow 200.

[0031] At step 210, fluid pressure data is acquired.

[0032] The fluid pressure data refers to the water pressure of multiple pipe network nodes in the urban water supply pipe network.

[0033] The pipe network node refers to a key node in the urban water supply pipe network. For example, the key node can include a water pipe, a connection point of the water pipe, a branch point, a turning point, or a control point in the urban water supply pipe network, etc.

[0034] In some embodiments, the multiple pipe network nodes of the urban water supply pipe network can be provided with fluid pressure monitoring devices, such as sensors, pressure gauges, etc. The processor can acquire the fluid pressure data based on the monitoring data of the fluid pressure monitoring devices.

[0035] At step 220, a pipe burst probability of the pipe network node is determined based on the fluid pressure data.

[0036] The pipe burst probability can measure the likelihood of the water pipe at the pipe network node bursting. For example, the higher the pipe burst probability, the greater the likelihood of the water pipe at the pipe network node bursting.

[0037] In some embodiments, the processor can determine the pipe burst probability of the pipe network node based on the fluid pressure data.

[0038] In some embodiments, for a pipe network node, the processor can determine the water pressure of the pipe network node based on the fluid pressure data, and then calculate a water pressure difference between the water pressure and a pressure threshold corresponding to the pipe network node. If the water pressure difference is positive, it can be determined that the pipe network node has a pipe burst risk. In some embodiments, the pipe burst probability is positively correlated with the water pressure difference, and the greater the water pressure difference, the greater the pipe burst probability.

[0039] If the water pressure difference is negative, it can be determined that the pipe burst risk of the pipe network node is low or does not exist, and the pipe burst probability can be set to 0.

[0040] The pressure threshold refers to a critical value for evaluating the possibility of the water pressure of the pipe network node causing the water pipe to burst. In some embodiments, the processor can acquire the pressure threshold corresponding to each pipe network node from the memory.

[0041] In some embodiments, the pressure threshold can be set by a technician according to experience.

[0042] For more information on determining the pipe burst probability, please refer to the relevant description of Figure 3 and Figure 4 .

[0043] At step 230, the target valve and its valve opening degree are determined based on the burst probability, and the target valve is controlled to the valve opening degree.

[0044] The target valve refers to a valve used to control the water pressure of a pipe network node with a burst probability greater than 0. In some embodiments, the valve closest to the pipe network node with a burst probability greater than 0 can be determined as the target valve. In some embodiments, the target valve includes an electric valve, such as an angular stroke electric valve, a straight stroke electric valve, etc.

[0045] The valve opening degree refers to the opening degree of the valve.

[0046] In some embodiments, the processor can determine the valve opening degree of the target valve based on the burst probability. For example, the valve opening degree can be positively correlated with the burst probability, and the greater the burst probability, the greater the valve opening degree.

[0047] In some embodiments, the processor can be communicatively connected with the target valve or its controller, and control the opening and closing of the target valve to the valve opening degree through communication.

[0048] In some embodiments, in response to the burst probability exceeding the probability threshold, the processor can determine a supply pressure adjustment parameter based on the burst probability, the supply pressure adjustment parameter including a target water pump, a target supply pressure, and a target water pump speed; and adjust the water pump speed of the target water pump to the target water pump speed according to the supply pressure adjustment parameter, so as to adjust the supply pressure of the pipe network to the target supply pressure.

[0049] The probability threshold refers to a critical probability for evaluating the burst of a pipe network node. In some embodiments, the processor can obtain the probability threshold corresponding to the pipe network node from the memory.

[0050] In some embodiments, the probability threshold can be set by a technician according to experience.

[0051] The supply pressure adjustment parameter refers to a parameter used to adjust the supply pressure of the water pump. In some embodiments, the supply pressure adjustment parameter can include at least one of a target water pump, a target supply pressure, and a target water pump speed, etc.

[0052] The target water pump refers to a water pump directly connected with a pipe network node with a burst probability greater than 0. In some embodiments, the target water pump can be determined by querying the first preset table or the second preset table.

[0053] For more information about the first preset table or the second preset table, see the relevant description later.

[0054] The target supply pressure refers to the pressure supply required to reduce the burst probability of the target water pump to below the probability threshold. In some embodiments, the target supply pressure can be determined based on the burst probability by querying the first preset table or the second preset table.

[0055] The target water pump rotating speed refers to the water pump rotating speed required to reduce the pipe burst probability of the target water pump to below the probability threshold. In some embodiments, the target water pump rotating speed can be determined based on the pipe burst probability by querying the first preset table or the second preset table.

[0056] In some embodiments, the processor can determine the supply pressure adjustment parameter based on the pipe burst probability in various ways. For example, the processor can determine the supply pressure adjustment parameter based on the first preset table.

[0057] The first preset table reflects the correspondence between each pipe network node distributed in the urban water supply pipe network, the pipe burst probability corresponding to the pipe network node, and the target water pump, the target supply pressure, and the target water pump rotating speed in the supply pressure adjustment parameter. In some embodiments, the processor can determine the target water pump, the target supply pressure, and the target water pump rotating speed corresponding to the pipe network node by querying the first preset table based on the pipe network node with a pipe burst probability greater than 0.

[0058] In some embodiments, the first preset table can be set by a technician according to experience or historical data. For example, the first preset table can be constructed with the historical target supply pressure and the historical target water pump rotating speed corresponding to the target water pump of the pipe network node with good prevention effect (e.g., no burst has occurred again) in the historical data. In some embodiments, the pipe burst probability can be negatively correlated with the target supply pressure and the target water pump rotating speed. For example, the greater the pipe burst probability, the lower the target supply pressure and the lower the target water pump rotating speed.

[0059] In some embodiments, the supply pressure adjustment parameter is related to at least one of the type of the target region, the region radius, the traffic volume of the target region, etc.

[0060] The target region refers to a region related to the pipe network node that needs to be further monitored. For more information about the target region, see the related description of Figure 3 .

[0061] The type of the target region can reflect information such as the traffic volume and the speed of the target region. For example, the type of the target region can be a highway, a main road, an intersection, etc.

[0062] In some embodiments, the processor can obtain the urban water supply pipe network distribution map from the memory and determine the type of the target region from the urban water supply pipe network distribution map. The urban water supply pipe network distribution map is a professional drawing that shows the spatial layout and connection relationship of water sources, pipe network nodes, pump stations, and auxiliary facilities in the urban water supply pipe network. In some embodiments, the urban water supply pipe network distribution map includes position information of a plurality of pipe network nodes, road information, etc.

[0063] The region radius refers to the radius of the target region established with the monitoring center as the center. For more information about the region radius and the monitoring center, see the related description of Figure 3 .

[0064] In some embodiments, the traffic volume of the target area is related to the type of the target area.

[0065] In some embodiments, the processor can further determine the traffic volume of the target area based on the road surface image. For example, the processor can calculate the number of vehicles passing by per unit time in the road surface image to determine the traffic volume of the target area.

[0066] For more information about the road surface image, please refer to the relevant description of Figure 3 .

[0067] In some embodiments, the processor can determine the supply pressure adjustment parameter through the second preset table.

[0068] The second preset table reflects the correspondence between each pipe network node distributed in the urban pipe network, the pipe burst probability corresponding to the pipe network node, the type of the target area where the pipe network node is located, the area radius, the traffic volume of the target area, and the target water pump, the target supply pressure, and the target water pump speed in the supply pressure adjustment parameter. The processor can determine the target water pump, the target supply pressure, and the target water pump speed corresponding to the pipe network node with a pipe burst probability greater than 0 by querying the second preset table based on the pipe network node with a pipe burst probability greater than 0, the pipe burst probability, the type of the target area where the pipe network node is located, the area radius, and the traffic volume of the target area.

[0069] In some embodiments, the second preset table can be set by technicians according to experience or historical data. For example, the historical target supply pressure and the historical target water pump speed corresponding to the target water pump of the pipe network node with good prevention effect (e.g., no burst has occurred again) in the historical data can be combined with the type of the historical target area where the target water pump is located, the historical area radius, and the traffic volume of the historical target area to construct the second preset table.

[0070] According to some embodiments of the present application, when adjusting the target supply pressure of the target water pump corresponding to the pipe network node with a pipe burst risk, the type of the area where the pipe network node is located, the area radius, and the traffic volume of the area are considered at the same time, which can more flexibly adjust the supply pressure of the target water pump for different areas. For example, in a high-risk area (e.g., a main road, a high-traffic area, etc.), the supply pressure of the target water pump can be reduced as soon as possible (e.g., when the pipe burst probability is at a lower value) to avoid the harm and loss caused by pipe burst, while in a low-risk area (e.g., a branch road, a low-traffic area, etc.), the supply pressure of the target water pump can be delayed (e.g., when the pipe burst probability is at a higher value) to avoid the influence of the reduced supply pressure of the water pump on downstream urban residents. Dynamic adjustment of the target supply pressure is achieved, the protection of high-risk areas is strengthened, and the efficient operation of urban pipe networks in low-risk areas is ensured.

[0071] In some embodiments, the processor can be communicatively connected with the target water pump or a controller thereof, and adjust the water pump rotating speed of the target water pump to a target water pump rotating speed based on the determined supply pressure adjustment parameter, so as to adjust the supply pressure of the pipe network to the target supply pressure.

[0072] According to some embodiments of the present application, by setting the supply pressure and water pump rotating speed of the target water pump to be automatically adjusted when the pipe burst probability of the pipe network node exceeds the probability threshold value, the required reduction value of the target water pump supply pressure can be accurately controlled, and the hydraulic impact risk in the pipe network caused by the sudden and large reduction of the supply pressure can be avoided. In addition, different target water pump supply pressures and water pump rotating speeds are set for different pipe network nodes and different pipe burst probabilities, which can improve the flexibility of supply pressure adjustment, and avoid excessive reduction of the supply pressure of the target water pump to affect the downstream urban residents.

[0073] According to some embodiments of the present application, by analyzing the fluid pressure data in the urban water supply pipe network, determining the pipe burst probability of each pipe network node, and determining the target valve and its valve opening degree based on the pipe burst probability, the target valve that needs to be controlled can be quickly and accurately located, and the opening degree of the target valve can be accurately controlled, so as to avoid the pipe corresponding to the pipe network node from bursting while reducing the impact on the urban residents.

[0074] Figure 3 is an example flowchart of generating a hedging instruction according to some embodiments of the present application. As shown in Figure 3 , the flow 300 includes the following steps. In some embodiments, the flow 300 can be executed by a processor.

[0075] Step 310, determining a target area based on the fluid pressure data.

[0076] In some embodiments, the processor can determine, as the target area, an area composed of multiple pipe network nodes whose water pressure in the fluid pressure data is greater than a pressure threshold value.

[0077] In some embodiments, the processor can determine the monitoring center and the area radius based on the fluid pressure data and the pressure threshold value, and determine the target area based on the monitoring center and the area radius.

[0078] For more information about the pressure threshold value, please refer to the related description of Figure 2 .

[0079] The monitoring center refers to the key monitoring point of the target area.

[0080] In some embodiments, for each node in the multiple pipe network nodes in the target area, the processor can determine the water pressure of the pipe network node based on the fluid pressure data, obtain the pressure threshold value corresponding to the pipe network node from the processor, and calculate the water pressure difference between the water pressure and the pressure threshold value.

[0081] In some embodiments, the processor selects, from the plurality of water pressure difference values of the plurality of pipe network nodes, a plurality of pipe network nodes with water pressure difference values greater than 0 as reference pipe network nodes. In some embodiments, the processor can construct a clustering vector with the water pressure difference value and the corresponding position coordinates of each reference pipe network node. In some embodiments, the position coordinates of the pipe network nodes can be obtained from the city water supply pipe network distribution map in the memory.

[0082] In some embodiments, the processor can cluster the plurality of clustering vectors corresponding to the plurality of reference pipe network nodes by a clustering algorithm to determine a plurality of cluster centers. The clustering algorithm can include, but is not limited to, K-Means clustering and / or density-based clustering method (DBSCAN), etc.

[0083] In some embodiments, the processor can select, from the plurality of cluster centers, a cluster center with a water pressure difference value greater than a difference threshold value as a candidate cluster center, and then sort the candidate cluster centers according to the size of the water pressure difference value, and take the position coordinates of the pipe network node corresponding to the candidate cluster center with the largest water pressure difference value as the monitoring center. The difference threshold value refers to the critical water pressure difference value for determining whether a cluster center can be a candidate cluster center.

[0084] In some embodiments, the difference threshold value can be set by the technician according to experience.

[0085] In some embodiments, the processor can determine the area radius based on the fluid pressure data of the monitoring center, for example, the area radius can be positively correlated with the water pressure difference value of the monitoring center, and the larger the water pressure difference value of the monitoring center, the larger the area radius.

[0086] In some embodiments, the processor can take the area covered by the monitoring center with the area radius as the target area.

[0087] According to some embodiments of the present application, by determining the pipe network nodes with water pressure difference values greater than 0 based on the water pressure and the pressure threshold value, constructing clustering vectors based on the water pressure difference values and the position coordinates of these pipe network nodes, determining cluster centers by a clustering algorithm, determining a monitoring center based on the cluster centers, determining an area radius based on the water pressure difference value of the monitoring center, and determining a target area based on the monitoring center and the area radius, the target area can be more reasonably and accurately determined, the monitoring resources (e.g., monitoring devices) in the target area can be more reasonably used, and the monitoring effect can be improved, for example, more comprehensive and accurate road surface images can be obtained.

[0088] For more information about fluid pressure data, please refer to the relevant description in Figure 2 .

[0089] Step 320, determining the corresponding target monitoring device and shooting parameter based on the target area.

[0090] The target monitoring device refers to the monitoring device in the target area. In some embodiments, the target monitoring device can include a camera, a video recorder, etc. In some embodiments, the processor can take the monitoring device located in the target area as the target monitoring device.

[0091] The shooting parameter refers to the parameter involved in the monitoring by the monitoring device. In some embodiments, the shooting parameter includes at least one of the target shooting angle and the target focal length, etc.

[0092] The target shooting angle refers to the shooting angle of the target monitoring device when shooting the target area. In some embodiments, the processor can determine the target shooting angle based on the initial shooting angle and the deflection angle, wherein the initial shooting angle is the preset shooting angle of the target monitoring device, and the deflection angle refers to the angle by which the target monitoring device needs to be deflected from the initial shooting angle to shoot the target area. In some embodiments, the processor can determine a virtual connecting line based on the position coordinates of the monitoring center and the position coordinates of the target monitoring device, and then determine a virtual straight line based on the lens orientation of the target monitoring device at the initial shooting angle, and determine the deflection angle as the angle between the virtual connecting line and the virtual straight line. In some embodiments, the processor can obtain the position coordinates of the target monitoring device from the memory, for example, the city monitoring device distribution map in the memory, which contains the type, distribution position, etc. of the monitoring device.

[0093] The target focal length refers to the focal length used by the target monitoring device when shooting the target area. In some embodiments, the processor can determine the target focal length based on the shooting distance between the target monitoring device and the monitoring center of the target area. In some embodiments, the target focal length is positively correlated with the shooting distance, for example, the farther the shooting distance, the longer the target focal length.

[0094] In some embodiments, the processor can determine the shooting distance between the target monitoring device and the monitoring center of the target area based on the monitoring image of the target area shot by the optical ranging technology, for example, the phase ranging method, similar triangle, etc.

[0095] Step 330, controlling the target monitoring device to adjust the shooting angle and the focal length based on the shooting parameter to obtain the road surface image of the target area.

[0096] The road surface image refers to the monitoring image of the road surface in the target area.

[0097] In some embodiments, the processor can control the lens of the target monitoring device to deflect by a deflection angle based on the target shooting angle and the initial shooting angle, so that the target monitoring device shoots the target area at the target shooting angle.

[0098] In some embodiments, the processor can control the target monitoring device to shoot the target area at the target focal length.

[0099] In some embodiments, the processor can perform image fusion on a plurality of monitoring images obtained by a plurality of target monitoring devices in the target area, to form a road surface image covering the target area. In some embodiments, the image fusion method can include but is not limited to Alpha fusion, Poisson fusion, etc.

[0100] In step 340, a road surface water seepage feature is determined based on the road surface image.

[0101] The road surface water seepage feature refers to a related feature of road surface water seepage in the target area. For example, water seepage position, water seepage flow, etc.

[0102] In some embodiments, the processor can determine the water seepage feature through image recognition technology. The image recognition technology includes but is not limited to Scale-invariant feature transform (SIFT) algorithm, deep learning technology, image segmentation technology, etc.

[0103] The water seepage position refers to the position of the water seepage point on the road surface. In some embodiments, the processor can determine the water seepage position through image recognition technology.

[0104] The water seepage flow refers to the water output of the water seepage point per unit time. In some embodiments, the processor can obtain images continuously shot by the target monitoring device per unit time, and determine the water seepage flow through image recognition technology based on the continuously shot images.

[0105] In step 350, a pipe burst probability of a pipe network node of the target area is determined based on the road surface water seepage feature and the fluid pressure data.

[0106] In some embodiments, the processor can determine the pipe network node corresponding to the water seepage position based on the water seepage position, and determine the water pressure of the pipe network node corresponding to the water seepage position based on the fluid pressure data, and then determine the water pressure difference value of the pipe network node corresponding to the water seepage position based on the water pressure.

[0107] For more information about the water pressure difference value, please refer to the related description of Figure 2 .

[0108] In some embodiments, the processor can normalize the water seepage flow and the water pressure difference value, and then perform weighted summation on the normalized water seepage flow and the water pressure difference value to obtain a pipe burst probability score.

[0109] For example, the pipe burst probability score can be obtained based on the following formula (1): (1) In formula (1), denotes the pipe burst probability score, denotes the normalized water seepage flow, denotes the normalized water pressure difference, and is a coefficient greater than 0, and the coefficient and can be preset based on prior experience.

[0110] In some embodiments, the pipe burst probability is positively correlated with the pipe burst probability score, and the higher the pipe burst probability score, the higher the pipe burst probability.

[0111] At step 360, in response to the pipe burst probability exceeding the probability threshold, a risk avoidance instruction is generated, and the risk avoidance instruction is broadcast to vehicles in the target area.

[0112] For more information about the probability threshold, see the related description of Figure 2 .

[0113] The risk avoidance instruction refers to a safety control instruction indicating that vehicles, pedestrians, etc. avoid danger. In some embodiments, the risk avoidance instruction includes a risk avoidance position.

[0114] The risk avoidance position refers to a position that needs to be avoided. In some embodiments, the processor can take the water seepage position as the risk avoidance position.

[0115] In some embodiments, the risk avoidance instruction further includes a broadcast intensity, and the broadcast intensity is related to the type of the target area and / or the type of the vehicle.

[0116] The broadcast intensity reflects the degree of urgency of the execution of the risk avoidance instruction. In some embodiments, the broadcast intensity includes at least one of the frequency, the duration, etc. of the broadcast.

[0117] In some embodiments, the processor can broadcast the risk avoidance instruction in various ways. For example, the risk avoidance instruction is broadcast through a voice broadcast device in the target monitoring device. For another example, the risk avoidance instruction is broadcast through a drone in the airspace above the target area. For another example, the risk avoidance instruction is broadcast through a vehicle-mounted radio device (e.g., a vehicle-mounted radio).

[0118] The vehicle types include common vehicles and special vehicles. The special vehicles refer to vehicles with special properties. The special vehicles include, but are not limited to, buses, school buses, dangerous goods transport vehicles, etc. The common vehicles refer to vehicles other than the special vehicles. In some embodiments, the processor can acquire traffic data images in a range based on the monitoring devices in the target area and the surrounding area (e.g., within 2 kilometers outside the target area), and identify the vehicle types of all vehicles in the traffic data images through image recognition technology.

[0119] For more information about the type of the target area, see the related description of Figure 2 .

[0120] In some embodiments, the processor can determine the broadcast strength in multiple ways. For example, the processor can determine the broadcast strength based on a third preset table.

[0121] The third preset table reflects the corresponding relationship between the type of the target area, the presence of special vehicles, and the broadcast playing frequency and duration. In some embodiments, the processor can determine the broadcast playing frequency and duration by querying the third preset table based on the type of the target area and the presence of special vehicles in the target area and the surrounding area. For example, if the type of the target area is a highway or a main road, the processor can reduce the broadcast playing frequency and duration to avoid distracting the drivers. For another example, if there are special vehicles in the target area and the surrounding area, the broadcast playing frequency can be increased to alert the drivers of the special vehicles as much as possible.

[0122] In some embodiments, the third preset table can be set by technicians according to experience.

[0123] According to some embodiments of the present application, the broadcast strength (e.g., playing frequency and playing duration) of the safety warning instruction can be dynamically adjusted according to the type of the target area and the types of the vehicles in the target area and the surrounding area, so as to reduce the interference to the drivers' attention while ensuring the safety alert effect, and to achieve precise warning for special target areas or special vehicles.

[0124] According to some embodiments of the present application, by combining the fluid pressure data and the road surface water seepage characteristics to analyze the pipe burst probability of the pipe network node, the high-risk area (i.e., the target area) can be dynamically determined, and the accuracy of judging the pipe burst probability can be improved; at the same time, the vehicles in the target area and the surrounding area can be broadcast in real time in combination with the risk avoidance instruction, so as to form a closed loop of "monitoring-analysis-warning-avoidance". Compared with the time lag of monitoring and warning caused by the traditional artificial inspection, some embodiments of the present application can improve the efficiency of monitoring and warning of the pipe burst probability of the pipe network, and also improve the safety of vehicles or personnel property. In addition, actively prompting the vehicles in the high-risk area to detour or brake can reduce the traffic accidents or economic losses caused by the pipe burst, and realize the technical upgrade from passive response to active avoidance of the safety protection of the urban water supply pipe network.

[0125] It should be noted that the above description of the process 300 is only for example and illustration, and does not limit the scope of application of the present application. Various modifications and changes can be made to the process 300 by those skilled in the art under the guidance of the present application. However, these modifications and changes are still within the scope of the present application. For example, the processor can dynamically adjust the shooting parameters based on the target area, in combination with the location, lighting conditions, etc. of the target area.

[0126] Figure 4 is an exemplary flowchart of determining the pipe burst probability according to some embodiments of the present application.

[0127] In some embodiments, the emergency supervision and management platform is further configured to: construct a pipe burst prediction graph 430 based on the road surface water seepage characteristics 410 and the fluid pressure data 420; determine a first pipe burst probability 450 of the pipe network node by a first prediction model 440 based on the pipe burst prediction graph 430; the first prediction model is a machine learning model; determine a second pipe burst probability 480 of the pipe network node by a second prediction model 470 based on the fluid pressure data 460 of the preset historical period; and determine the pipe burst probability 490 of the pipe network node by weighted fusion based on the first pipe burst probability 450 and the second pipe burst probability 480.

[0128] The pipe burst prediction graph refers to a knowledge graph representing the potential risk distribution of pipe burst of each node of the pipe network.

[0129] In some embodiments, the emergency supervision and management platform can construct a pipe burst prediction graph based on the road surface water seepage characteristics and the fluid pressure data. For more details about the road surface water seepage characteristics and the fluid pressure, see Figure 2 and the related description.

[0130] In some embodiments, the pipe burst prediction graph can be composed of at least one node and at least one edge, and the node has corresponding node characteristics.

[0131] In some embodiments, the node includes a pipe network node, a water seepage node. More about the pipe network node, see step 210 and its related description. The water seepage node corresponds to the water seepage position in the road surface water seepage feature.

[0132] In some embodiments, the node features of the pipe network node can include the fluid pressure data corresponding to the node and the water pipe material. The node features of the water seepage node can include the road surface water seepage feature.

[0133] In some embodiments, the water pipe material can be obtained by querying the material list in the construction drawings or the completion acceptance report of the city underground pipe network.

[0134] In some embodiments, the edges of the pipe burst prediction graph include first type edges and second type edges. The first type edges are used to connect the pipe network nodes. In some embodiments, if there is a physical connection relationship between the pipe network nodes, there is a first type edge between them. Wherein, the physical connection relationship refers to the topological association that the pipe network nodes are directly connected in physics or connected through pipe auxiliary equipment (such as valves, tees, flanges, etc.) and form a continuous water flow path. The edge features of the first type edge include the pressure difference between the two pipe network nodes. The second type edges are used to connect the pipe network nodes and the water seepage nodes. In some embodiments, if the physical distance between the water seepage node and the pipe network node is less than the distance threshold, there is a second type edge between them, wherein the distance threshold can be set by the person skilled in the art according to experience. The edge features of the second type edge include the physical distance.

[0135] The first pipe burst probability is a parameter representing the pipe burst possibility obtained by fusing the spatial structure of the pipe network.

[0136] In some embodiments, the emergency management platform can determine the first pipe burst probability of the pipe network node based on the pipe burst prediction graph through a first prediction model.

[0137] The first prediction model refers to a model used to predict the first pipe burst probability of the pipe network node. In some embodiments, the first prediction model is a machine learning model. For example, the first prediction model can include one or more combinations of a deep neural network (DNN) model or a convolutional neural network (CNN) model or other custom models.

[0138] In some embodiments, the input of the first prediction model can be the pipe burst prediction graph, and the output of the first prediction model can be the first pipe burst probability of the pipe network node.

[0139] In some embodiments, the first prediction model can be trained by a plurality of first training samples with first labels to obtain an initial first prediction model. The first training samples can include a burst pipe prediction graph corresponding to a first historical time point. The first labels can include a condition of whether a pipe network node actually bursts in a time period from the first historical time point to a second historical time point under the first training sample. The first historical time point is prior to the second historical time point. In some embodiments, for a pipe network node that bursts in the time period from the first historical time point to the second historical time point, the longer the time interval from the first historical time point to the burst time of the pipe network node, the lower the value of the first burst pipe probability of the pipe network node. For a pipe network node that does not burst, the first burst pipe probability is zero.

[0140] In some embodiments, the first training samples and the first labels can be obtained based on historical data.

[0141] In some embodiments, the emergency supervision and management platform can input a plurality of first training samples with first labels into the initial first prediction model, construct a loss function based on the first labels and the results of the initial first prediction model, and update the parameters of the initial first prediction model by gradient descent or other methods based on the loss function. When a preset condition is met, the model training is completed, and a trained first prediction model is obtained. The preset condition can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0142] The second burst pipe probability is a parameter representing the possibility of burst pipe obtained by fusing the time series prediction of the pipe network.

[0143] In some embodiments, the emergency supervision and management platform can determine the second burst pipe probability of the pipe network node based on the fluid pressure data of a preset historical period by the second prediction model.

[0144] The preset historical period refers to a time interval with a pre-set time range. In some embodiments, the preset historical period can be a period of time before the current time. In some embodiments, the preset historical period can be set by the experience of a person skilled in the art.

[0145] In some embodiments, the length of the preset historical period is related to the road surface water seepage feature and the water seepage threshold.

[0146] The water seepage threshold refers to a parameter for judging whether the water seepage flow is normal. In some embodiments, the water seepage threshold can be set by the experience of a person skilled in the art.

[0147] In some embodiments, the greater the difference between the water seepage flow in the road surface water seepage feature and the water seepage threshold, the shorter the length of the preset historical period.

[0148] In some embodiments of the present application, the time length of the preset historical period is related to the pavement water seepage feature and the water seepage threshold. When the difference between the pavement water seepage feature and the water seepage threshold increases, it indicates that the degree of pavement water seepage is aggravated, and the risk of pipe burst is significantly increased. At this time, the time length of the preset historical period can be shortened accordingly, so as to improve the calculation efficiency, speed up the system response speed, and realize more timely early warning and disposal.

[0149] The second prediction model refers to a model for predicting the second pipe burst probability of the pipe network node. In some embodiments, the second prediction model is a machine learning model. For example, the second prediction model can include one or more combinations of a Deep Neural Network (DNN) model or a Convolutional Neural Network (CNN) model or other custom models.

[0150] In some embodiments, the input of the second prediction model can be the fluid pressure data of the pipe network node in the preset historical period, and the output of the second prediction model can be the second pipe burst probability of the pipe network node.

[0151] In some embodiments, the second prediction model can be obtained by training an initial second prediction model through a plurality of sets of second training samples with second labels. The second training sample can include the fluid pressure data of the sample pipe network node in a first preset time period in the historical data. The second label can include the actual pipe burst situation of the sample pipe network node in a second preset time period after the first preset time period. If a pipe burst occurs, the second label takes a value of 1, and if not, it takes a value of 0. The length of the first preset time period is the same as the length of the preset historical period, and the second preset time period can be set by a person skilled in the art according to experience.

[0152] In some embodiments, the second training sample and the second label can be obtained based on the historical data.

[0153] The training process of the second prediction model is similar to that of the first prediction model, and the specific training process is described above.

[0154] In some embodiments, the emergency supervision and management platform can perform weighted fusion based on the first pipe burst probability and the second pipe burst probability of the pipe network node to determine the pipe burst probability of the pipe network node. For more details about the pipe burst probability, see step 220 and its related description.

[0155] In some embodiments, the weighted fusion can be calculated by formula (2), as shown below. (2) In formula (2), P represents the pipe burst probability of the pipe network node. a first burst probability representing a pipe network node; a weight representing the first burst probability; a second burst probability representing a pipe network node; a weight representing the second burst probability; and satisfies .

[0156] In some embodiments, the weight of the second burst probability in the weighted fusion is related to the area radius. For more information about the area radius, see step 310 and its related description.

[0157] In some embodiments, the greater the area radius, the greater the weight of the second burst probability.

[0158] In some embodiments of the present application, the weight of the second burst probability is related to the area radius. As the area radius increases, the load of the monitoring device can increase accordingly; while the effectiveness of the identification of the road surface water seepage feature can decrease due to the non-uniformity of its spatial distribution. Therefore, increasing the weight of the second burst probability based on the fusion of time series prediction helps to improve the reliability of the burst probability prediction.

[0159] In some embodiments of the present application, by constructing a burst prediction map and fusing fluid pressure data, the first prediction model models and analyzes the pipe network structure from the spatial dimension, outputting the first burst probability representing the spatial risk distribution; at the same time, based on the fluid pressure time series data of the preset historical period, the second prediction model captures the pressure dynamic evolution law from the time dimension, outputting the second burst probability representing the time dimension. Finally, the system generates the comprehensive burst probability of the pipe network node by weighted fusion of the above-mentioned prediction results of the time and space dual dimensions (i.e. the first burst probability and the second burst probability). This spatio-temporal coupling prediction method effectively overcomes the limitations of traditional single-dimensional (only spatial or only temporal) evaluation models, and comprehensively utilizes the pipe network topological structure information and historical pressure change characteristics, significantly improving the accuracy and reliability of the burst probability prediction.

[0160] The foregoing detailed description has been set forth to explain the basic concepts in a manner that is considered by the patentee to be most effective in promoting an understanding of the application. It will be apparent, however, to those skilled in the art that various modifications, improvements and developments can be made in the present application without departing from the spirit and scope of the application. Such modifications, improvements and developments are intended to be included within the spirit and scope of the exemplary embodiments of the present application.

[0161] At the same time, the present invention uses specific terms to describe embodiments of the present invention. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a certain feature, structure, or characteristic associated with at least one embodiment of the present invention. Therefore, it should be emphasized and noted that the use of "one embodiment," "an embodiment," or "an alternative embodiment" mentioned twice or more in different places in the present invention does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the present invention may be appropriately combined.

[0162] 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.

[0163] Similarly, it should be noted that, in order to simplify the presentation of the present disclosure and facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of the invention sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of the invention requires more features than those recited in the claims. In practice, an embodiment may have fewer features than the totality of the features of a single embodiment disclosed above.

[0164] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present invention are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0165] Each of the patents, patent applications, patent publications, and other materials, such as articles, books, specifications, publications, documents and the like, cited herein are hereby incorporated by reference in their entirety. Any application history file that is inconsistent with or that renders unclear the content of the present application is excluded. Any application history file that limits the broadest scope of the claims of the present application is excluded. It is specifically intended that the description, definitions, and / or terminology used in the application incorporated by reference be used in accordance with the description, definitions, and / or terminology used in the present application, if there is any inconsistency.

[0166] Finally, it should be understood that the embodiments described herein are merely exemplary of the application. Other variations of the embodiments can also be possible and are within the scope of the present application. Thus, for example, an alternative configuration of the embodiments of the present application can be considered as consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to the embodiments specifically introduced and described herein.

Claims

1. A city lifeline pipe network burst prevention system based on the Internet of Things large model, characterized by: The system includes an emergency supervision and management platform, which is configured to: Obtain fluid pressure data; Determining the probability of pipe burst at a pipe network node based on the fluid pressure data; and A target valve and its valve opening are determined based on the pipe burst probability, and the target valve is controlled to the valve opening.

2. The system according to claim 1, wherein: The emergency supervision management platform is further configured to: determining a target area based on the fluid pressure data; Determining a corresponding target monitoring device and shooting parameters based on the target area; Controlling the target monitoring device to adjust a shooting angle and a focal length based on the shooting parameters to acquire a road surface image of the target area; determining a road surface water seepage characteristic based on the road surface image; Determining the pipe burst probability of the pipe network node in the target area based on the road surface water seepage characteristics and the fluid pressure data; as well as, In response to the squib probability exceeding a probability threshold, an avoidance instruction is generated and broadcast to vehicles in the target area.

3. The system according to claim 2, characterized in that The emergency supervision management platform is further configured to: Determining a monitoring center and an area radius based on the fluid pressure data and a pressure threshold; The target area is determined based on the monitoring center and the area radius.

4. The system according to claim 2, wherein: The emergency supervision management platform is further configured to: Constructing a pipe burst prediction map based on the road surface water seepage characteristics and the fluid pressure data; Based on the pipe burst prediction map, determining a first pipe burst probability of the pipe network node by using a first prediction model; the first prediction model is a machine learning model; Determining a second pipe burst probability of the pipe network node based on the fluid pressure data of a preset historical period using a second prediction model; and The pipe burst probability of the pipe network node is determined by performing weighted fusion based on the first pipe burst probability and the second pipe burst probability.

5. The system according to claim 1, wherein: The emergency supervision management platform is further configured to: In response to the burst probability exceeding a probability threshold, Determining supply pressure adjustment parameters based on the pipe burst probability, the supply pressure adjustment parameters including a target water pump, a target supply pressure, and a target water pump speed; and The water pump speed of the target water pump is adjusted to the target water pump speed according to the supply pressure adjustment parameter, so as to adjust the supply pressure of the pipeline network to the target supply pressure.

6. A method for preventing urban lifeline pipe network bursts based on the Internet of Things large model, characterized in that: This is achieved through a city lifeline pipe network burst prevention system based on an Internet of Things large model. The method includes: Obtain fluid pressure data; Determining the probability of pipe burst at a pipe network node based on the fluid pressure data; and A target valve and its valve opening are determined based on the pipe burst probability, and the target valve is controlled to the valve opening.

7. The method according to claim 6, characterized in that Determining the pipe burst probability of a pipe network node based on the fluid pressure data includes: determining a target area based on the fluid pressure data; Determining a corresponding target monitoring device and shooting parameters based on the target area; Controlling the target monitoring device to adjust a shooting angle and a focal length based on the shooting parameters to acquire a road surface image of the target area; determining a road surface water seepage characteristic based on the road surface image; Determining the pipe burst probability of the pipe network node in the target area based on the road surface water seepage characteristics and the fluid pressure data; and In response to the squib probability exceeding a probability threshold, an avoidance instruction is generated and broadcast to vehicles in the target area.

8. The method according to claim 7, characterized in that Determining the target area based on the fluid pressure data includes: Determining a monitoring center and an area radius based on the fluid pressure data and a pressure threshold; The target area is determined based on the monitoring center and the area radius.

9. The method according to claim 7, characterized in that The determining, based on the road surface water seepage characteristics and the fluid pressure data, the pipe burst probability of the pipe network node in the target area includes: Constructing a pipe burst prediction map based on the road surface water seepage characteristics and the fluid pressure data; Based on the pipe burst prediction map, determining a first pipe burst probability of the pipe network node by using a first prediction model; the first prediction model is a machine learning model; Determining a second pipe burst probability of the pipe network node based on the fluid pressure data of a preset historical period using a second prediction model; and The pipe burst probability of the pipe network node is determined by performing weighted fusion based on the first pipe burst probability and the second pipe burst probability.

10. The method according to claim 6, characterized in that The method further includes: In response to the burst probability exceeding a probability threshold, Determining supply pressure adjustment parameters based on the pipe burst probability, the supply pressure adjustment parameters including a target water pump, a target supply pressure, and a target water pump speed; and The water pump speed of the target water pump is adjusted to the target water pump speed according to the supply pressure adjustment parameter, so as to adjust the supply pressure of the pipeline network to the target supply pressure.

Images