Urban hydropower pipe network safety monitoring method, device, home host and system

Abstract

The invention relates to an urban water and electricity pipe network safety monitoring method, device, home host and system, and the method comprises the steps: obtaining water and electricity data collected by a home terminal, and carrying out the extraction based on the water and electricity data to obtain abnormal feature data; receiving abnormal feature data shared by other home hosts in the intelligent joint defense network, and performing group intelligent analysis on the received abnormal feature data and the abnormal feature data extracted by the group intelligent analysis model by using the group intelligent analysis model to identify a space-time association relationship of abnormal propagation of the urban hydropower pipe network; according to the time-space association relationship, determining whether the urban water and electricity pipe network has a regional disaster or not; under the condition that regional disasters exist in the urban hydropower pipe network, according to the types of the regional disasters, an alarm mode matched with the types of the regional disasters is adopted for alarming. Therefore, the regional disasters of the urban hydropower pipe network can be accurately identified, and the regional disaster prevention and control capability is improved.

Description

Technical Field

[0001] This application relates to the field of urban water and electricity pipeline safety monitoring technology, and in particular to a method, device, home host and system for urban water and electricity pipeline safety monitoring. Background Technology

[0002] Currently, existing methods for monitoring the safety of urban water and electricity networks typically rely on smart water meters and smart electricity meters in households for real-time monitoring. However, this approach only allows for independent monitoring of each household's water and electricity network, failing to enable collaborative analysis of data across different households. Consequently, it cannot identify regional disasters, resulting in a low regional disaster prevention and control capability for existing urban water and electricity network safety monitoring methods. Therefore, improving regional disaster prevention and control capabilities has become an urgent technical problem to be solved. Summary of the Invention

[0003] This application provides a method, device, home host, and system for safety monitoring of urban water and electricity pipeline networks, in order to address the problem of low regional disaster prevention and control capabilities of existing urban water and electricity pipeline network safety monitoring methods.

[0004] In a first aspect, embodiments of this application provide a method for safety monitoring of urban water and electricity pipeline networks, applicable to any home host in a smart joint defense network, wherein the smart joint defense network is a distributed cluster formed by multiple home hosts based on the physical topology of the urban water and electricity pipeline network, and the method includes:

[0005] The system acquires water and electricity data collected from its own household devices and extracts abnormal feature data based on the water and electricity data.

[0006] It receives abnormal feature data shared by other home hosts in the intelligent joint defense network, and uses a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself, so as to identify the spatiotemporal correlation of the abnormal propagation of the urban water and electricity pipeline network.

[0007] Based on the spatiotemporal correlation, determine whether the urban water and electricity pipeline network is subject to regional disasters;

[0008] In the event of a regional disaster in the city's water and electricity pipeline network, an alarm will be issued using an alarm method that matches the type of regional disaster.

[0009] Optionally, the regional disasters include household-level disasters, neighborhood-level disasters, and community-level disasters;

[0010] The step of determining whether the urban water and electricity network is subject to regional disasters based on the spatiotemporal correlation includes:

[0011] When the spatiotemporal correlation characterizes an anomaly in the water and electricity network only at the household level, it is determined that the urban water and electricity network suffers the household-level disaster; and / or

[0012] When multiple households on the same branch road simultaneously experience water and electricity network anomalies, as indicated by the spatiotemporal correlation, it is determined that the urban water and electricity network suffers from a neighborhood-level disaster; and / or

[0013] When multiple household terminals across branch lines simultaneously exhibit abnormalities in the water and electricity pipeline network, as characterized by the spatiotemporal correlation, it is determined that the urban water and electricity pipeline network is experiencing a community-level disaster.

[0014] Optionally, the step of issuing an alarm using an alarm method that matches the type of the regional disaster includes:

[0015] In the case where the regional disaster is classified as a household-level disaster, an alarm is issued using both sound and light, and emergency handling guidelines are pushed to the user terminals connected to the system; and / or

[0016] In the event that the regional disaster is classified as a neighborhood-level disaster, the linked neighborhood home host switches to emergency mode and broadcasts evacuation notices to users of the neighborhood home host, wherein the neighborhood home host refers to a home host located on the same branch road as itself; and / or

[0017] In the case where the regional disaster is classified as a community-level disaster, a diagnostic report is generated by integrating data from the community home host and then pushed to the community property control room and the terminals of emergency repair personnel. The community home host refers to a home host located in the same community as the host.

[0018] Optionally, the step of acquiring water and electricity data collected from the household terminal and extracting abnormal feature data based on the water and electricity data includes:

[0019] Obtain water and electricity data collected from your own household device;

[0020] Time-domain analysis and frequency-domain analysis were performed on the hydropower data to obtain the time-domain and frequency-domain characteristics of the hydropower data.

[0021] The abnormal feature data that is abnormal is identified from the time domain features and the frequency domain features.

[0022] Optionally, after identifying the anomalous feature data from the time-domain features and the frequency-domain features, the method further includes:

[0023] The abnormal feature data is desensitized;

[0024] The anonymized abnormal feature data is shared with other home hosts in the intelligent joint defense network, so that these hosts can receive the anonymized abnormal feature data and perform swarm intelligence analysis based on it; and / or

[0025] The anomaly data after anonymization is uploaded to the cloud platform, which then performs federated learning on the anomaly data to obtain the model parameters of the optimized swarm intelligence analysis model. The optimized swarm intelligence analysis model parameters are then distributed to each home host in the intelligent joint defense network.

[0026] Optionally, before performing swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself using a swarm intelligence analysis model to identify the spatiotemporal correlation of the abnormal propagation in the urban water and electricity pipeline network, the method further includes:

[0027] Obtain municipal data from the municipal platform;

[0028] The municipal data, the received abnormal feature data, and the abnormal feature data extracted by itself are fused to obtain fused data;

[0029] The step of using a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself, and identifying the spatiotemporal correlation of the abnormal propagation in the urban water and electricity pipeline network, includes:

[0030] The swarm intelligence analysis model is used to perform swarm intelligence analysis on the fused data to identify the spatiotemporal correlation of abnormal propagation in the urban water and electricity pipeline network.

[0031] Secondly, this application also provides a safety monitoring device for urban water and electricity pipeline networks, applied to any home host in a smart joint defense network. The smart joint defense network is a distributed cluster formed by multiple home hosts based on the physical topology of the urban water and electricity pipeline network. The device includes:

[0032] The first acquisition module is used to acquire water and electricity data collected from its own household terminal, and extract abnormal feature data based on the water and electricity data;

[0033] The analysis module is used to receive abnormal feature data shared by other home hosts in the intelligent joint defense network, and to use a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself, so as to identify the spatiotemporal correlation of the abnormal propagation of the urban water and electricity pipeline network.

[0034] The determination module is used to determine whether there is a regional disaster in the urban water and electricity pipeline network based on the spatiotemporal correlation.

[0035] The alarm module is used to issue an alarm in the event of a regional disaster in the urban water and electricity pipeline network, based on the type of regional disaster, using an alarm method that matches the type of regional disaster.

[0036] Thirdly, this application also provides a home host, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0037] Memory, used to store computer programs;

[0038] The processor, when executing a program stored in memory, implements the urban water and electricity pipeline safety monitoring method described in the first aspect.

[0039] Fourthly, this application also provides an urban water and electricity pipeline network safety monitoring system, which includes an intelligent joint defense network. The intelligent joint defense network is a distributed cluster formed by multiple home hosts as described in the third aspect based on the physical topology of the urban water and electricity pipeline network.

[0040] Optionally, the urban water and electricity pipeline safety monitoring system also includes a cloud platform and a municipal platform, and each home host in the intelligent joint defense network is communicatively connected to the cloud platform and the municipal platform;

[0041] In this system, each home host in the intelligent joint defense network is used to upload the anonymized abnormal feature data to the cloud platform; the cloud platform is used to perform federated learning on the anonymized abnormal feature data to obtain the model parameters of the optimized swarm intelligence analysis model, and then distribute the optimized swarm intelligence analysis model parameters to each home host in the intelligent joint defense network.

[0042] The municipal platform is used to provide municipal data; each home host in the intelligent joint defense network is also used to obtain municipal data from the municipal platform; the municipal data, the received abnormal feature data and the abnormal feature data extracted by itself are fused to obtain fused data; the swarm intelligence analysis model is used to perform swarm intelligence analysis on the fused data to identify the spatiotemporal correlation of abnormal propagation in the urban water and electricity pipeline network.

[0043] Compared with the prior art, the technical solution provided in this application has the following advantages: The method provided in this application acquires water and electricity data collected by its own home terminal and extracts abnormal feature data based on the water and electricity data; receives abnormal feature data shared by other home hosts in the intelligent joint defense network, and uses a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself to identify the spatiotemporal correlation of abnormal propagation in the urban water and electricity pipeline network; determines whether there is a regional disaster in the urban water and electricity pipeline network based on the spatiotemporal correlation; and, in the case of a regional disaster in the urban water and electricity pipeline network, uses an alarm method that matches the type of regional disaster to issue an alarm based on the type of regional disaster. Through the above methods, each home host can use a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself, thereby identifying the spatiotemporal correlation of abnormal propagation in urban water and electricity pipelines. This enables accurate identification of regional disasters in urban water and electricity pipelines, thereby improving the regional disaster prevention and control capabilities and effectively solving the problem of low regional disaster prevention and control capabilities of existing urban water and electricity pipeline safety monitoring methods. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0045] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0047] Figure 1 A flowchart illustrating a method for safety monitoring of urban water and electricity pipeline networks provided in this application embodiment;

[0048] Figure 2 A flowchart illustrating another method for safety monitoring of urban water and electricity pipeline networks provided in this application embodiment;

[0049] Figure 3 A schematic diagram of the structure of an urban water and electricity pipeline safety monitoring device provided in this application embodiment;

[0050] Figure 4 This application provides a schematic diagram of the structure of a home console.

[0051] Figure 5 This is a schematic diagram of the structure of an urban water and electricity pipeline safety monitoring system provided in an embodiment of this application. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0053] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0054] To address the issue of low regional disaster prevention capabilities in existing urban water and electricity pipeline safety monitoring methods, this application provides an urban water and electricity pipeline safety monitoring method, device, home host, and system, which can improve regional disaster prevention capabilities.

[0055] See Figure 1 , Figure 1 This is a flowchart illustrating a method for safety monitoring of urban water and electricity pipeline networks, provided as an embodiment of this application. Figure 1 As shown, this urban water and electricity pipeline network safety monitoring method is applied to any home host in an intelligent joint defense network. The intelligent joint defense network is a distributed cluster formed by multiple home hosts based on the physical topology of the urban water and electricity pipeline network. The urban water and electricity pipeline network safety monitoring method may include the following steps:

[0056] Step S101: Obtain water and electricity data collected from your own home terminal, and extract abnormal feature data based on the water and electricity data.

[0057] Specifically, the aforementioned water and electricity data may include, but is not limited to, data such as water pressure, flow rate, current, and voltage. This water and electricity data can be collected by various sensing devices (such as water pressure sensors, flow sensors, smart meters, etc.) and then transmitted to the corresponding home control unit. In this way, the home control unit can obtain its own home's water and electricity data. The aforementioned abnormal characteristic data refers to abnormal characteristic data identified through time-domain and frequency-domain analysis of the water and electricity data, such as characteristic data indicating a continuous drop in water pressure or characteristic data indicating voltage fluctuations.

[0058] Step S102: Receive abnormal feature data shared by other home hosts in the intelligent joint defense network, and use a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself to identify the spatiotemporal correlation of abnormal propagation in the urban water and electricity pipeline network.

[0059] Specifically, the aforementioned swarm intelligence analysis model is an artificial intelligence model inspired by the collective behavior of biological groups in nature (such as ant colonies, bird flocks, and bee colonies). It aims to solve complex problems by simulating group collaboration and self-organization. Its core idea is to generate global intelligence through the local interactions of a large number of simple individuals, thereby accomplishing tasks that are difficult for a single individual to achieve. This swarm intelligence analysis model is used to dynamically deduce the direction and speed of anomaly propagation by combining physical laws, preset rules, and real-time data, thereby identifying the spatiotemporal correlations of anomaly propagation in urban water and electricity pipeline networks.

[0060] Step S103: Based on the spatiotemporal correlation, determine whether there are regional disasters in the urban water and electricity pipeline network.

[0061] Specifically, the aforementioned regional disasters refer to disasters caused by small-area failures in urban water and electricity pipelines. Based on the size of the affected area, regional disasters can be categorized into household-level disasters, neighborhood-level disasters, and community-level disasters.

[0062] Based on spatiotemporal correlations, home servers can determine their own location, the water and electricity network anomalies of neighboring home servers on the same branch road, and community home servers in the same community, thereby determining whether there are regional disasters in the city's water and electricity network.

[0063] Step S104: In the event of a regional disaster in the urban water and electricity pipeline network, an alarm method matching the type of regional disaster shall be used to issue an alarm.

[0064] In the event of regional disasters affecting urban water and electricity networks, home control units can issue alarms using alarm methods that match the type of regional disaster. This allows for different alarm methods to be used for different types of regional disasters. This introduces a real-time dynamic response mechanism, linking early warning and emergency resources across home control units, optimizing the traditional chain-like response process into a parallel response mode, and significantly improving disaster prevention and control efficiency.

[0065] Through the above methods, each home host can use a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself, thereby identifying the spatiotemporal correlation of abnormal propagation in urban water and electricity pipelines. This enables accurate identification of regional disasters in urban water and electricity pipelines, thereby improving the regional disaster prevention and control capabilities and effectively solving the problem of low regional disaster prevention and control capabilities of existing urban water and electricity pipeline safety monitoring methods.

[0066] In one optional embodiment, regional disasters include household-level disasters, neighborhood-level disasters, and community-level disasters;

[0067] Step S103 above, based on spatiotemporal correlation, determines whether there are regional disasters in the urban water and electricity network, including:

[0068] When the spatiotemporal correlation characterization indicates that only the household's water and electricity network is abnormal, it is determined that there is a household-level disaster in the city's water and electricity network; and / or

[0069] When multiple households on the same branch road simultaneously exhibit anomalies in their water and electricity pipe networks, indicating a spatiotemporal correlation, it is determined that a neighborhood-level disaster exists in the urban water and electricity pipe network; and / or

[0070] When multiple household terminals across branch lines exhibit simultaneous anomalies in their water and electricity pipelines, it is determined that a community-level disaster exists in the urban water and electricity pipeline network.

[0071] Specifically, if the spatiotemporal correlation indicates that only the household's water and electricity network is abnormal, it indicates an intra-household water and electricity network anomaly that does not affect other branch roads and main pipelines outdoors. In this case, a household-level disaster can be identified in the urban water and electricity network. If the spatiotemporal correlation indicates that multiple households on the same branch road simultaneously experience water and electricity network anomalies, a neighborhood-level disaster can be identified in the urban water and electricity network. For example, if cross-checking of the mains of three households (A, B, and C) on the same branch road reveals that household A experiences a drop in water pressure, household B experiences reduced water flow, and household C experiences abnormal sound signatures, then a leak in the main water pipe in the corridor between A and B can be identified. If the spatiotemporal correlation indicates that multiple households across branch roads simultaneously experience water and electricity network anomalies, a community-level disaster can be identified in the urban water and electricity network, such as regional network aging or the impact of extreme weather.

[0072] The above methods can accurately identify the types of regional disasters, making it easier to use appropriate alarm methods to issue alarms based on the types of regional disasters.

[0073] In an optional embodiment, step S104, which involves issuing an alarm using an alarm method that matches the type of regional disaster, includes:

[0074] In cases where the regional disaster is classified as a household-level disaster, an audible and visual alarm is issued, and emergency handling guidelines are pushed to user terminals connected to the system; and / or

[0075] In the event of a neighborhood-level disaster, the system will switch all neighborhood home servers to emergency mode and broadcast evacuation notices to their users. A neighborhood home server refers to a home server located on the same branch road as the host; and / or

[0076] In the case of a regional disaster classified as a community-level disaster, a diagnostic report is generated by integrating data from the community home host and then pushing the diagnostic report to the community property control room and the terminals of emergency repair personnel. The community home host refers to a home host located in the same community as the host.

[0077] Specifically, if the regional disaster is a household-level disaster (such as a leaking angle valve), an alarm can be issued using sound and light, and emergency handling guidelines (such as closing the corresponding zone valves) can be pushed to the user terminals connected to it. If the regional disaster is a neighborhood-level disaster (such as a broken main water pipe in a building corridor), the neighborhood home host can be linked to switch to emergency mode (such as simultaneously closing the smart valves of the faulty branch to prevent the disaster from spreading), and evacuation prompts can be broadcast to users of the neighborhood home host via power line broadcast. If the regional disaster is a community-level disaster (such as a substation grounding fault), the community home host will be linked to perform data fusion to generate a diagnostic report, which will be pushed to the community property control room and the terminals of emergency repair personnel. This diagnostic report can include a three-dimensional (3D) location map of the affected pipelines and recommended handling solutions.

[0078] In this way, by introducing a real-time dynamic response mechanism, and by linking early warning and emergency resources among various home hosts, the traditional chain-like handling process is optimized into a parallel response mode, significantly improving the efficiency of disaster prevention and control.

[0079] In an optional embodiment, step S101, acquiring water and electricity data collected from the user's own household terminal, and extracting abnormal feature data based on the water and electricity data, includes:

[0080] Obtain water and electricity data collected from your own household device;

[0081] Time-domain and frequency-domain analyses were performed on the hydropower data to obtain the corresponding time-domain and frequency-domain characteristics of the hydropower data.

[0082] Identify anomalous feature data from time-domain and frequency-domain features.

[0083] Specifically, the home host, acting as an edge computing node, possesses edge computing capabilities. It can acquire water and electricity data collected from its own home terminals, and then perform time-domain and frequency-domain analyses on this data to obtain corresponding time-domain characteristics (such as water pressure fluctuations, current fluctuations, etc.) and frequency-domain characteristics (such as pipe vibration frequencies, acoustic signatures, etc.). Next, it identifies anomalous data features from these time-domain and frequency-domain characteristics. Here, water and electricity data can refer to one or more of water pressure, flow rate, current, and voltage, or a combination of these, or a combination with other data.

[0084] In this way, each home host can extract abnormal feature data based on the water and electricity data collected by its own home terminal, which facilitates subsequent anomaly analysis of its own home's water and electricity pipelines and sharing with other home hosts for collective intelligent analysis.

[0085] In an optional embodiment, after the above steps of identifying anomalous feature data from time-domain and frequency-domain features, the method further includes:

[0086] Desensitize abnormal feature data;

[0087] The anomaly data, after being anonymized, is shared with other home hosts in the smart network, so that these hosts can receive the anomaly data and perform swarm intelligence analysis based on it; and / or

[0088] The anomaly data after anonymization is uploaded to the cloud platform, which then performs federated learning on the anomaly data to obtain the model parameters of the optimized swarm intelligence analysis model. The optimized swarm intelligence analysis model parameters are then distributed to each home host in the smart joint defense network.

[0089] Specifically, after extracting anomalous feature data, the home host can perform anonymization processing on the data. This anonymization process includes one or more combinations of encryption and access control. The anonymized anomalous feature data can then be shared with other home hosts in the smart network. These other home hosts can then receive the anonymized data and perform collective intelligent analysis based on it. This approach successfully resolves the conflict between privacy protection and data collaboration by simultaneously protecting user privacy and achieving efficient data collaboration and risk warning.

[0090] In addition, home hosts can upload anonymized anomalous feature data to the cloud platform. The cloud platform can then perform federated learning on this data to obtain optimized swarm intelligence analysis model parameters (such as fault detection thresholds and feature weights), and distribute these parameters to each home host in the intelligent network. This allows for the fusion of anomalous feature data from different home hosts, enabling continuous optimization of the swarm intelligence analysis model.

[0091] In an optional embodiment, before step S102, which involves using a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself to identify the spatiotemporal correlation of abnormal propagation in the urban water and electricity pipeline network, the method further includes:

[0092] Obtain municipal data from the municipal platform;

[0093] The municipal data, the received abnormal feature data, and the abnormal feature data extracted by itself are fused to obtain fused data;

[0094] Step S102: Utilize a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by the system itself, identifying the spatiotemporal correlation of abnormal propagation in the urban water and electricity pipeline network, including:

[0095] By using a swarm intelligence analysis model to perform swarm intelligence analysis on fused data, the spatiotemporal correlation of abnormal propagation in urban water and electricity pipeline networks can be identified.

[0096] Specifically, the home computer can also acquire municipal data from the municipal platform, then fuse the municipal data, received abnormal feature data, and its own extracted abnormal feature data to obtain fused data. Next, a swarm intelligence analysis model is used to perform swarm intelligence analysis on the fused data to identify the spatiotemporal correlations of abnormal propagation in the urban water and electricity pipeline network. In this way, by fusing high-frequency data from the home terminal with macroscopic data from the municipal platform, the spatiotemporal correlations of abnormal propagation in the urban water and electricity pipeline network can be better identified, enabling precise tracing of regional disasters.

[0097] In an optional embodiment, the urban water and electricity pipeline safety monitoring process provided in this application is as follows: Figure 2 As shown, it may include the following steps:

[0098] Step S201: Deployment and networking of the home host.

[0099] New water and electricity hazard detection devices are designed for each household. For example, the water monitoring system uses intelligent, integrated units that can be installed at key nodes of the main inlet valve without damaging the pipes. It detects leakage risks by dynamically sensing changes in water flow (such as pressure fluctuations, flow rate changes, acoustic spectrum changes, pipe wall vibration changes, temperature field changes, and water flow impedance spectrum changes). The circuit monitoring device is innovatively adapted to different sizes of distribution boxes, tracking circuit anomalies in real time in a non-contact manner (such as short circuit faults, leakage risks, overload hazards, power quality risks, and equipment coupling interference). Water and electricity hazard detection devices are preferentially deployed at vulnerable locations such as water pipe bends and line junctions. When each household unit is installed, it can automatically perform over-location based on the community's water and electricity network geographic information system (GIS) map and establish point-to-point communication links between different household units along the actual water and electricity network pipeline routes. This automatically constructs an intelligent joint prevention network that matches the physical network, ensuring that abnormal signals are accurately transmitted to the relevant households along the actual water and electricity paths. Abnormal signals here can be automatically relayed according to the direction of medium propagation (water leak reporting downstream, circuit fault tracing upstream, etc.). In this way, each household host can perform cluster collaborative verification. For example, if three adjacent household hosts cross-confirm and find that household A has a drop in water pressure, household B has a decrease in water flow, and household C has an abnormal sound signature, they can identify a risk of leakage in the pipe section between A and B.

[0100] Step S202: Gradual construction of the joint defense network.

[0101] Initial network (when the user base is small): Home hosts are installed to form independent monitoring nodes. By comparing the differences between municipal data and home data (such as the difference between the total water consumption of the community and the sum of water consumption of each household), the probability of anomalies in the uncovered areas is estimated and potential risk areas are marked.

[0102] Growth-stage network (medium user base): Neighboring households' home control units automatically form joint defense groups, utilizing the physical connection characteristics of pipelines to construct local inference chains. When abnormal fluctuations occur in a certain section of pipeline, based on the location and data change gradient of the installed home control units, the system intelligently infers the state parameters of pipelines in households without installed home control units, achieving point-to-area hazard localization.

[0103] Mature Network (with a large user base): Home hosts in the covered areas construct a high-precision digital mirror of the pipeline network. Through machine learning analysis of the correlation between user behavior patterns and device feedback, it autonomously generates virtual monitoring data for homes without home hosts installed, ultimately forming a comprehensive, blind-spot-free joint defense system. As the user base grows, continuous optimization occurs, and collaborative analysis capabilities gradually increase. This mechanism creates a positive feedback loop between network performance and user scale, naturally evolving into a complete water and electricity safety protection network through gradual data accumulation and device interconnection.

[0104] Step S203: Distributed collaborative analysis to determine the regional disaster type.

[0105] When an anomaly is detected in a household, the system automatically retrieves recent data from neighboring units on the same branch line, analyzing parameters such as the propagation speed of pressure fluctuations and abnormal current phase shifts to distinguish between indoor faults and problems in the shared pipeline. For example, if a household detects a continuous drop in water pressure, the system automatically compares it with the water pressure curves of upstream neighbors. If the anomaly is found to propagate backward along the pipeline, it is determined to be a leak in the municipal main pipeline rather than an indoor problem. Home control units use a consensus algorithm to confirm cross-household associated risks. When three or more control units independently detect related anomalies, a joint prevention and control alert is automatically triggered.

[0106] Step S204: When the regional disaster type is a household-level disaster, execute the household-level response.

[0107] When an individual indoor fault is detected (such as a leaking angle valve), the home control unit immediately sounds an alarm with both sound and light, and pushes a handling guide (such as closing the corresponding zone valve) through the application (APP).

[0108] Step S205: When the regional disaster type is a neighborhood-level disaster, execute a neighborhood-level response.

[0109] When three or more household mainframes confirm a branch-level risk (such as a cracked main water pipe in the building corridor), the emergency mode of all household mainframes on this line is automatically activated: the branch-level smart valves are closed simultaneously to prevent the disaster from spreading, and evacuation notices are sent to affected residents via power line broadcast.

[0110] Step S206: When the regional disaster type is a community-level disaster, execute a community-level response.

[0111] When a systemic risk across branch lines is detected (such as a substation grounding fault), the home host cluster will integrate multi-dimensional data to generate a diagnostic report, which will be directly pushed to the property control room and the terminals of emergency repair personnel, along with a 3D location map of the affected pipelines and a recommended handling plan.

[0112] Step S207: Self-optimizing joint defense network.

[0113] At the device level, the home unit automatically performs sensor calibration monthly, identifies its own monitoring deviations by comparing data from neighboring units on the same network, and implements dynamic compensation. At the network level, after each alert event, each home unit uploads anonymized data to the cloud platform, and optimizes local model parameters through federated learning. Simultaneously, a device contribution evaluation system is established, assigning higher decision-making weight to home units that consistently achieve leading accuracy, forming an energy-efficiency-oriented autonomous network.

[0114] The urban water and electricity pipeline safety monitoring method provided in this application sinks intelligent analysis capabilities to home hosts and utilizes the natural topological relationships formed by the physical pipeline network to construct a distributed joint prevention network. This avoids the cross-household transmission of sensitive data and can accurately identify the propagation path of water and electricity anomalies. Compared with traditional centralized monitoring systems, the neighborhood joint prevention model can improve the speed of early warning of water and electricity leaks, while reducing the cost of municipal inspections and forming a new infrastructure maintenance ecosystem with active resident participation.

[0115] See Figure 3 , Figure 3 This is a schematic diagram of the structure of a safety monitoring device for urban water and electricity pipeline networks provided in an embodiment of this application. Figure 3 As shown, the urban water and electricity pipeline safety monitoring device 300 is applied to any home host in the intelligent joint defense network. The intelligent joint defense network is a distributed cluster formed by multiple home hosts based on the physical topology of the urban water and electricity pipeline network. The urban water and electricity pipeline safety monitoring device 300 includes:

[0116] The first acquisition module 301 is used to acquire water and electricity data collected by its own household terminal, and extract abnormal feature data based on the water and electricity data;

[0117] Analysis module 302 is used to receive abnormal feature data shared by other home hosts in the intelligent joint defense network, and to use a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself, so as to identify the spatiotemporal correlation of abnormal propagation in the urban water and electricity pipeline network.

[0118] Module 303 is used to determine whether there are regional disasters in the urban water and electricity pipeline network based on spatiotemporal correlation.

[0119] The alarm module 304 is used to issue an alarm in the event of a regional disaster in the urban water and electricity pipeline network, and to use an alarm method that matches the type of regional disaster.

[0120] Furthermore, regional disasters include household-level disasters, neighborhood-level disasters, and community-level disasters; module 303 includes:

[0121] The first determination submodule is used to determine whether there is a household-level disaster in the city's water and electricity network when the spatiotemporal correlation characterization shows that only the household itself has water and electricity network anomalies.

[0122] The second determination submodule is used to determine the presence of neighborhood-level disasters in the urban water and electricity network when multiple household terminals on the same branch road have abnormalities at the same time in terms of spatiotemporal correlation.

[0123] The third determination submodule is used to determine the existence of community-level disasters in the urban water and electricity network when multiple household terminals across branches have anomalies in the spatiotemporal correlation characterization.

[0124] Furthermore, alarm module 304 includes:

[0125] The first alarm submodule is used to issue an alarm in the form of sound and light when the type of regional disaster is household-level disaster, and push emergency handling guidelines to the user terminals connected to it.

[0126] The second alarm sub-module is used to link the neighborhood home host to switch to emergency mode and broadcast evacuation notices to the users of the neighborhood home host when the type of regional disaster is neighborhood-level disaster. The neighborhood home host refers to the home host located on the same branch road as itself.

[0127] The third alarm sub-module is used to generate a diagnostic report by linking the community home host after data fusion when the regional disaster type is a community-level disaster. The diagnostic report is then pushed to the community property control room and the terminal of the emergency repair personnel. The community home host refers to the home host located in the same community.

[0128] Furthermore, the first acquisition module 301 includes:

[0129] The acquisition submodule is used to acquire water and electricity data collected from its own home terminal. The water and electricity data includes at least one of water pressure, flow rate, current and voltage.

[0130] The analysis submodule is used to perform time-domain and frequency-domain analysis on hydropower data to obtain the time-domain and frequency-domain characteristics of the hydropower data.

[0131] The identification submodule is used to identify anomalous feature data from time-domain and frequency-domain features.

[0132] Furthermore, the city's water and electricity pipeline safety monitoring device 300 also includes:

[0133] The desensitization module is used to desensitize abnormal feature data, wherein the desensitization process includes at least one of encryption and access control.

[0134] The sharing module is used to share anonymized anomaly data with other home hosts in the smart network, so that these hosts can receive the anonymized data and perform swarm intelligence analysis based on it; and / or

[0135] The upload module is used to upload the anonymized abnormal feature data to the cloud platform, so that the cloud platform can perform federated learning on the anonymized abnormal feature data to obtain the model parameters of the optimized swarm intelligence analysis model, and then send the optimized swarm intelligence analysis model parameters to each home host in the smart joint defense network.

[0136] Furthermore, the city's water and electricity pipeline safety monitoring device 300 also includes:

[0137] The second acquisition module is used to acquire municipal data from the municipal platform;

[0138] The fusion module is used to fuse municipal data, received abnormal feature data, and abnormal feature data extracted by itself to obtain fused data;

[0139] Analysis module 302 is also used to perform swarm intelligence analysis on the fused data using a swarm intelligence analysis model to identify the spatiotemporal correlation of abnormal propagation in urban water and electricity pipeline networks.

[0140] It should be noted that the urban water and electricity pipeline safety monitoring device 300 can realize the urban water and electricity pipeline safety monitoring method provided in the aforementioned method embodiments and can achieve the same technical effect, which will not be elaborated here.

[0141] like Figure 4 As shown in the illustration, this application also provides a home host system, including a processor 411, a communication interface 412, a memory 413, and a communication bus 414, wherein the processor 411, the communication interface 412, and the memory 413 communicate with each other via the communication bus 414.

[0142] Memory 413 is used to store computer programs;

[0143] In one embodiment of this application, the processor 411, when executing the program stored in the memory 413, implements the urban water and electricity pipeline safety monitoring method provided in any of the foregoing method embodiments.

[0144] like Figure 5 As shown in the embodiment of this application, a safety monitoring system for urban water and electricity pipelines is also provided. The urban water and electricity pipeline safety monitoring system 500 includes an intelligent joint defense network 501, which is a distributed cluster formed by multiple home hosts, such as those in the third aspect, based on the physical topology of the urban water and electricity pipeline network.

[0145] Each household deploys multiple sensors (such as water pressure, flow rate, current, and temperature) to collect water and electricity data in real time and send it to its respective home control unit. Each home control unit acts as an edge computing node, collecting water and electricity data within the household in real time. Utilizing edge computing capabilities, it performs preliminary data processing and feature extraction to identify potential anomalies. Home control units share anonymized anomaly characteristic data through local communication protocols (such as Mesh networks), building a regional data network. Home control units use swarm intelligence analysis models to simulate the collaborative behavior of distributed intelligent agents, analyzing anomaly patterns and propagation laws in the data, i.e., identifying the spatiotemporal correlations of anomalies, such as the propagation path of pressure fluctuations or the phase shift of current anomalies. Home control units assess anomalies in the data in real time, determining whether they represent regional risks. Combining this with the pipeline network topology, they predict the areas that anomalies may affect, providing accurate early warning information. Based on the risk assessment results, they trigger corresponding emergency response mechanisms, gradually expanding from the household level to the community level.

[0146] In this way, the Smart Joint Defense Network 501 can monitor, identify anomalies, and provide early warnings for urban water and electricity networks in real time, while ensuring data security and privacy protection, thereby effectively improving the security of urban infrastructure.

[0147] Further, see also Figure 5 The city's water and electricity pipeline safety monitoring system 500 also includes a cloud platform 502 and a municipal platform 503. Each home host in the intelligent joint defense network 501 is connected to the cloud platform 502 and the municipal platform 503.

[0148] Among them, each home host in the intelligent joint defense network 501 is used to upload the de-identified abnormal feature data to the cloud platform 502; the cloud platform 502 is used to perform federated learning on the de-identified abnormal feature data to obtain the model parameters of the optimized swarm intelligence analysis model, and then distribute the model parameters of the optimized swarm intelligence analysis model to each home host in the intelligent joint defense network 501.

[0149] The municipal platform 503 is used to provide municipal data; each home host in the intelligent joint defense network 501 is also used to obtain municipal data from the municipal platform 503; the municipal data, the received abnormal feature data and the abnormal feature data extracted by itself are fused to obtain fused data; the swarm intelligence analysis model is used to perform swarm intelligence analysis on the fused data to identify the spatiotemporal correlation of abnormal propagation in the urban water and electricity pipeline network.

[0150] Specifically, a lightweight protocol conversion layer can be developed to establish a data interface between the home host and the municipal platform 503, ensuring compatibility with heterogeneous sensor data of varying precision and frequency. Specifically, a protocol adapter module capable of recognizing and parsing multiple communication protocols used by the home host can be developed; the data format transmitted by the home host can be converted into a standard format (such as JSON, XML, etc.) understandable by the municipal platform 503; efficient compression algorithms or fragmentation techniques can be employed to reduce data transmission latency and packet loss risks; the protocol conversion layer can be tested in a real-world environment to ensure compatibility with various devices and platforms and data accuracy; encrypted transmission and authentication can be implemented to guarantee data security during conversion and transmission; and an upgradeable and expandable structure can be designed to adapt to new protocols or sensor types that may emerge in the future.

[0151] The Urban Water and Electricity Pipeline Safety Monitoring System 500 can leverage edge computing nodes to extract regional risk features, resolving the conflict between privacy protection and data collaboration. Specifically, by extracting regional risk features at edge computing nodes, it can achieve efficient data collaboration and risk early warning while protecting user privacy. Localized processing and encrypted transmission ensure data security, while collaborative analysis and dynamic model updates improve the accuracy and response speed of risk identification, successfully resolving the conflict between privacy protection and data collaboration.

[0152] When constructing the urban water and electricity pipeline safety monitoring system 500, smart sensors can be deployed at key nodes in each household (such as the main inlet valve and distribution box) to monitor the real-time operating status of the water and electricity pipeline, including key parameters such as water pressure, flow rate, and current. High-density deployment of home-level sensors ensures comprehensive and real-time data collection, reducing monitoring blind spots. Each household is equipped with a home host with edge computing capabilities, enabling real-time analysis of sensor data and extraction of abnormal features (such as water pressure fluctuations and current anomalies). Preliminary data analysis is performed at the home host, reducing data transmission latency and improving response speed. For example, if a continuous drop in water pressure is detected, it immediately determines whether it is an indoor fault. Based on the physical pipeline layout of the community, an intelligent joint defense network 501 is automatically constructed to ensure that abnormal signals are transmitted to relevant households along the actual water and electricity paths. When a household detects an anomaly, the intelligent joint defense network 501 quickly transmits the signal to neighboring households, forming a rapid response mechanism. The home host automatically performs sensor calibration monthly, comparing data from neighboring units on the same line to identify monitoring deviations and implementing dynamic compensation.

[0153] The cloud platform 502 incorporates a federated learning mechanism, which optimizes local model parameters through federated learning, improves the accuracy of anomaly detection, and establishes a device contribution evaluation system. It assigns higher decision weight to home hosts that consistently lead in accuracy, forming an energy-efficiency-oriented autonomous network.

[0154] Therefore, the 500 urban water and electricity pipeline safety monitoring system has the following beneficial effects:

[0155] 1. By constructing a high-density, multi-level monitoring network, the monitoring data at the household and municipal levels are effectively integrated, significantly improving the safety of urban infrastructure.

[0156] 2. Advanced swarm intelligence analysis technology has been introduced, which can analyze multi-source heterogeneous data in real time, accurately identify regional risks, and thus achieve early warning.

[0157] 3. A privacy protection mechanism was designed to ensure that family data is not leaked during the sharing process, balancing the needs of data security and collaborative analysis.

[0158] 4. By optimizing the early warning response process, the system can quickly locate problems and initiate emergency measures, significantly shortening the time from anomaly detection to problem resolution and improving the city's emergency response capabilities for public safety incidents.

[0159] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the urban water and electricity pipeline safety monitoring method provided in any of the foregoing method embodiments.

[0160] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0161] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0162] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0163] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for safety monitoring of urban water and electricity pipeline networks, characterized in that, The method applies to any home host in a smart joint defense network, wherein the smart joint defense network is a distributed cluster formed by multiple home hosts based on the physical topology of an urban water and electricity pipeline network, and includes: The system acquires water and electricity data collected from its own household devices and extracts abnormal feature data based on the water and electricity data. It receives abnormal feature data shared by other home hosts in the intelligent joint defense network, and uses a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself, so as to identify the spatiotemporal correlation of the abnormal propagation of the urban water and electricity pipeline network. Based on the spatiotemporal correlation, determine whether the urban water and electricity pipeline network is subject to regional disasters; In the event of a regional disaster in the city's water and electricity pipeline network, an alarm will be issued using an alarm method that matches the type of regional disaster.

2. The method according to claim 1, characterized in that, The regional disasters mentioned include household-level disasters, neighborhood-level disasters, and community-level disasters; The step of determining whether the urban water and electricity network is subject to regional disasters based on the spatiotemporal correlation includes: When the spatiotemporal correlation characterizes an anomaly in the water and electricity network only at the household level, it is determined that the urban water and electricity network suffers the household-level disaster; and / or When multiple households on the same branch road simultaneously experience water and electricity network anomalies, as indicated by the spatiotemporal correlation, it is determined that the urban water and electricity network suffers from a neighborhood-level disaster; and / or When multiple household terminals across branch lines simultaneously exhibit abnormalities in the water and electricity pipeline network, as characterized by the spatiotemporal correlation, it is determined that the urban water and electricity pipeline network is experiencing a community-level disaster.

3. The method according to claim 2, characterized in that, The step of issuing an alarm based on the type of the regional disaster, using an alarm method that matches the type of the regional disaster, includes: In the case where the regional disaster is classified as a household-level disaster, an alarm is issued using both sound and light, and emergency handling guidelines are pushed to the user terminals connected to the system; and / or In the event that the regional disaster is classified as a neighborhood-level disaster, the linked neighborhood home host switches to emergency mode and broadcasts evacuation notices to users of the neighborhood home host, wherein the neighborhood home host refers to a home host located on the same branch road as itself; and / or In the case where the regional disaster is classified as a community-level disaster, a diagnostic report is generated by integrating data from the community home host and then pushing the diagnostic report to the community property control room and the terminals of emergency repair personnel. The community home host refers to a home host located in the same community as the host.

4. The method according to claim 1, characterized in that, The process of acquiring water and electricity data collected from one's own household terminal, and extracting abnormal feature data based on the water and electricity data, includes: Obtain water and electricity data collected from your own household device; Time-domain analysis and frequency-domain analysis were performed on the hydropower data to obtain the time-domain and frequency-domain characteristics of the hydropower data. The abnormal feature data that is abnormal is identified from the time domain features and the frequency domain features.

5. The method according to claim 4, characterized in that, After identifying the anomalous feature data from the time-domain features and the frequency-domain features, the method further includes: The abnormal feature data is desensitized; The anonymized abnormal feature data is shared with other home hosts in the intelligent joint defense network, so that these hosts can receive the anonymized abnormal feature data and perform swarm intelligence analysis based on it; and / or The anomaly data after anonymization is uploaded to the cloud platform, which then performs federated learning on the anomaly data to obtain the model parameters of the optimized swarm intelligence analysis model. The optimized swarm intelligence analysis model parameters are then distributed to each home host in the intelligent joint defense network.

6. The method according to claim 5, characterized in that, Before using a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself to identify the spatiotemporal correlation of the abnormal propagation in the urban water and electricity pipeline network, the method further includes: Obtain municipal data from the municipal platform; The municipal data, the received abnormal feature data, and the abnormal feature data extracted by itself are fused to obtain fused data; The step of using a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself, and identifying the spatiotemporal correlation of the abnormal propagation in the urban water and electricity pipeline network, includes: The swarm intelligence analysis model is used to perform swarm intelligence analysis on the fused data to identify the spatiotemporal correlation of abnormal propagation in the urban water and electricity pipeline network.

7. A safety monitoring device for urban water and electricity pipeline networks, characterized in that, The device is applied to any home host in a smart joint defense network, wherein the smart joint defense network is a distributed cluster formed by multiple home hosts based on the physical topology of the urban water and electricity pipeline network, and the device includes: The first acquisition module is used to acquire water and electricity data collected from its own household terminal, and extract abnormal feature data based on the water and electricity data; The analysis module is used to receive abnormal feature data shared by other home hosts in the intelligent joint defense network, and to use a swarm intelligence analysis model to perform swarm intelligence analysis on the received abnormal feature data and the abnormal feature data extracted by itself, so as to identify the spatiotemporal correlation of the abnormal propagation of the urban water and electricity pipeline network. The determination module is used to determine whether there is a regional disaster in the urban water and electricity pipeline network based on the spatiotemporal correlation. The alarm module is used to issue an alarm in the event of a regional disaster in the urban water and electricity pipeline network, based on the type of regional disaster, using an alarm method that matches the type of regional disaster.

8. A home console, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the urban water and electricity pipeline safety monitoring method according to any one of claims 1-6.

9. A safety monitoring system for urban water and electricity pipeline networks, characterized in that, The urban water and electricity pipeline safety monitoring system includes an intelligent joint defense network, which is a distributed cluster formed by multiple home hosts as described in claim 8 based on the physical topology of the urban water and electricity pipeline network.

10. The urban water and electricity pipeline safety monitoring system according to claim 9, characterized in that, The urban water and electricity pipeline safety monitoring system also includes a cloud platform and a municipal platform, and each home host in the intelligent joint defense network is communicatively connected to the cloud platform and the municipal platform; In this system, each home host in the intelligent joint defense network is used to upload the anonymized abnormal feature data to the cloud platform; the cloud platform is used to perform federated learning on the anonymized abnormal feature data to obtain the model parameters of the optimized swarm intelligence analysis model, and then distribute the optimized swarm intelligence analysis model parameters to each home host in the intelligent joint defense network. The municipal platform is used to provide municipal data; each home host in the intelligent joint defense network is also used to obtain municipal data from the municipal platform; the municipal data, the received abnormal feature data and the abnormal feature data extracted by itself are fused to obtain fused data; the swarm intelligence analysis model is used to perform swarm intelligence analysis on the fused data to identify the spatiotemporal correlation of abnormal propagation in the urban water and electricity pipeline network.

Images