Power grid disaster monitoring and early warning cooperative system, method, equipment and medium
By using collaborative systems and multi-source data analysis, the problems of single monitoring methods and insufficient data analysis in power grid disaster monitoring have been solved, enabling timely and accurate early warning of power grid disasters and intelligent operation and maintenance.
Patent Information
- Application Number
- CN202511818159.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-04
- Publication Date
- 2026-02-10
AI Technical Summary
Existing power grid disaster monitoring methods are limited in scope and lack coordination, with insufficient depth of data analysis, resulting in low accuracy and timeliness of early warnings.
The system employs a collaborative approach involving local monitoring subsystems, mobile inspection subsystems, satellite monitoring subsystems, and a cloud data platform. Through feature mining and correlation analysis, it combines drone and satellite imagery data to provide comprehensive early warnings and constructs a power grid disaster operation and maintenance knowledge base, while also integrating meteorological data.
It enables timely and accurate early warning of power grid disasters, improves the accuracy and timeliness of monitoring, and supports intelligent operation and maintenance and rapid repair.
Smart Images
Figure CN121505834A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power grid monitoring technology, and in particular to a collaborative method, equipment, and medium for power grid disaster monitoring and early warning. Background Technology
[0002] The safe and stable operation of the power grid is of paramount importance. Power grid disasters (such as wildfires, floods, geological disasters, and foreign object intrusion) seriously threaten the safety of power grid equipment and may trigger large-scale power outages. Therefore, timely and accurate monitoring and early warning of power grid disasters are crucial to ensuring the reliability of the power grid.
[0003] Currently, power grid disaster monitoring mainly relies on two technical approaches. The first involves deploying various sensors (such as tilt sensors, image monitoring devices, and micro-weather stations) at key locations like transmission line corridors, towers, and substations, using fixed data thresholds to identify anomalies and issue alerts. The second relies on maintenance personnel conducting regular ground or drone inspections to identify potential hazards through on-site surveys or reviewing inspection images. In addition, some advanced solutions are beginning to explore the use of satellite remote sensing data for wide-area disaster identification.
[0004] However, the aforementioned existing technical solutions have significant shortcomings: First, the monitoring methods are singular and lack coordination. Ground sensors have limited monitoring range and fixed perspectives; while satellite remote sensing has a wide coverage, its revisit cycle is long and susceptible to cloud interference, making it difficult to meet real-time requirements; UAV inspections are usually carried out according to fixed plans, lacking intelligent linkage with other monitoring methods. Each system often operates independently, with data and alarm information scattered, failing to form a three-dimensional monitoring and collaborative verification capability. Second, the depth of data analysis is insufficient, and the foresight of early warning is weak. Existing methods mostly rely on simple threshold comparisons or isolated analysis of single-source data (such as images), lacking deep fusion and correlation mining of multi-source, heterogeneous monitoring data (such as sensor time-series data, meteorological data, and remote sensing image features). This makes it difficult for the system to accurately identify early risk signs from complex dynamic environments, and it is also unable to effectively simulate the development path of disaster chains. The accuracy and timeliness of early warnings need to be improved, often resulting in false alarms, missed alarms, or delayed warnings. Summary of the Invention
[0005] This invention provides a collaborative method, equipment, and medium for power grid disaster monitoring and early warning, which addresses the problems of existing monitoring methods being singular and lacking in synergy, as well as insufficient data analysis depth, resulting in low accuracy and timeliness of early warnings.
[0006] In view of this, the first aspect of the present invention provides a collaborative system for power grid disaster monitoring and early warning, the system comprising:
[0007] The local monitoring subsystem is used to acquire local monitoring data of the area where the power grid equipment is located and send it to the data service center;
[0008] The data service center is used to preprocess the local monitoring data, and based on the processed local monitoring data, to predict power grid disasters through feature mining and correlation analysis, and to issue power grid disaster warnings through a preset local early warning model. When a power grid disaster warning is detected in a certain area, the mobile inspection subsystem is triggered, and when a disaster is predicted to occur in a certain location, the satellite monitoring subsystem is triggered.
[0009] Based on a pre-set anomaly monitoring model, disaster confirmation is performed on areas where power grid disaster warnings may be issued based on video monitoring data; and specific areas where disasters may occur are obtained based on satellite imagery.
[0010] The mobile inspection subsystem is used to control drones to conduct inspections, obtain video monitoring data of areas where there may be early warnings of power grid disasters, and transmit the data back to the data service center.
[0011] The satellite monitoring subsystem is used to acquire satellite images of locations where power grid disasters may occur and transmit them back to the data service center;
[0012] The cloud-based data platform is used to store monitoring data, prediction results, and early warning results collected by the data service center, as well as the algorithm models used for early warning and prediction.
[0013] Optionally, it may also include: a maintenance work order system;
[0014] The maintenance work order system is used to receive maintenance work orders, real-time monitoring data of the maintenance area where the maintenance work order is located, and disaster emergency response model, and send them to the terminal carried by the staff, so that the staff can perform maintenance on the maintenance area according to the maintenance work order, the real-time monitoring data, and the disaster emergency response model and return the maintenance results to the data service center;
[0015] The maintenance work order, the real-time monitoring data, and the disaster emergency response model are issued by the data service center, and the maintenance work order is generated based on power grid disaster early warning.
[0016] Optionally, it also includes: a third-party interface for accessing a third-party system, enabling the third-party system to issue early warnings for power grid disasters based on real-time monitoring data and return the early warning results after responding to the early warning command.
[0017] Optionally, the mobile inspection subsystem is further configured to: upon responding to a timed inspection command, control the drone to perform inspections along a preset route according to a preset inspection cycle, and upload the inspection data to the data service center, so that the data service center can perform anomaly monitoring based on the inspection data obtained from the timed inspections.
[0018] Optionally, the satellite monitoring subsystem is further configured to: upon responding to an anomaly monitoring command, perform a similarity matching comparison between real-time satellite images of the environment in which the power grid to be monitored is located and historical satellite images, and determine whether there is an anomaly in the environment in which the area to be monitored is located based on the comparison results.
[0019] Optionally, the satellite monitoring subsystem is further configured to: trigger the mobile inspection subsystem when there is an anomaly in the environment of the area to be inspected, so that the mobile inspection subsystem controls the drone to inspect the area to be inspected.
[0020] Optionally, the local monitoring subsystem specifically includes: a sensor module, a local main control module, and a local data communication module; wherein, the sensor module is installed in the power grid equipment or the area where the power grid is located;
[0021] The local master control module is used to control the sensor module to monitor the power grid equipment or the area where the power grid is located after responding to the monitoring command, and to send the monitoring results to the data service center through the local data communication module.
[0022] A second aspect of the present invention provides a collaborative method for power grid disaster monitoring and early warning, the method comprising:
[0023] S1. Obtain local monitoring data of the area where the power grid equipment is located, and preprocess the local monitoring data;
[0024] S2. Based on the processed local monitoring data, power grid disaster prediction is performed through feature mining and correlation analysis, and power grid disaster early warning is performed through a preset local early warning model. When a power grid disaster early warning is detected in a certain area, step S3 is executed. When a disaster is predicted to occur in a certain location, step S4 is executed.
[0025] S3. Use drones to conduct inspections and obtain video monitoring data of areas where there may be power grid disaster warnings. Based on a preset anomaly monitoring model, confirm the disaster in the areas where there may be power grid disaster warnings according to the video monitoring data.
[0026] S4. Obtain satellite images of locations where power grid disasters may occur, and obtain specific areas where disasters may occur based on the satellite images.
[0027] A third aspect of the present invention provides a collaborative device for power grid disaster monitoring and early warning, the device comprising a processor and a memory:
[0028] The memory is used to store program code and transmit the program code to the processor;
[0029] The processor is configured to execute the steps of the collaborative method for power grid disaster monitoring and early warning as described in the second aspect above, according to the instructions in the program code.
[0030] A fourth aspect of the present invention provides a computer-readable storage medium for storing program code for executing the collaborative method for power grid disaster monitoring and early warning described in the second aspect above.
[0031] As can be seen from the above technical solutions, the present invention has the following advantages:
[0032] This invention provides a collaborative system for power grid disaster monitoring and early warning. On one hand, it utilizes coordinated air, space, and ground monitoring to achieve early warning of power grid disasters, addressing the problem of untimely monitoring caused by relying on single data thresholds. Simultaneously, this invention leverages big data mining and modeling to integrate multi-source data for comprehensive early warning of power grid disasters, improving the accuracy of monitoring and early warning, making monitoring more timely, and achieving early warning. Furthermore, it integrates with a maintenance work order system to enable the issuance and feedback of maintenance work orders; and it constructs a power grid disaster operation and maintenance knowledge base to enable intelligent operation and maintenance questioning, helping repair personnel quickly find operation and maintenance knowledge for rapid repairs. On the other hand, it includes a third-party interface, connecting to a meteorological workstation to obtain meteorological data, thus diversifying the data source for power grid disaster monitoring. This invention solves the problems of existing monitoring methods being singular and lacking coordination, as well as insufficient data analysis depth, leading to low accuracy and timeliness of early warnings. Attached Figure Description
[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0034] Figure 1 This is a schematic diagram of the structure of a collaborative system for power grid disaster monitoring and early warning provided in an embodiment of the present invention;
[0035] Figure 2This is a flowchart illustrating a collaborative method for power grid disaster monitoring and early warning provided in an embodiment of the present invention. Detailed Implementation
[0036] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.
[0037] Please see Figure 1 The present invention provides a collaborative system for monitoring and early warning of power grid disasters, comprising: a local monitoring subsystem 101, a data service center 102, a mobile inspection subsystem 103, a satellite monitoring subsystem 104, and a cloud data platform 105;
[0038] It should be noted that the data service center, as the data processing center of the entire collaborative system, is responsible for data integration, analysis, mining, and model building. It communicates with the local monitoring subsystem, mobile inspection subsystem, and satellite monitoring subsystem to integrate local monitoring data, inspection data, and satellite monitoring data, thereby achieving collaborative monitoring across air, space, and ground, and improving real-time monitoring and early warning of power grid disasters.
[0039] See the following instructions for details:
[0040] The local monitoring subsystem 101 is used to acquire local monitoring data of the area where the power grid equipment is located and send it to the data service center;
[0041] In one embodiment, the local monitoring subsystem 101 specifically includes: a sensor module, a local main control module, and a local data communication module; wherein the sensor module is located in the power grid equipment or the area where the power grid is located. The local main control module, upon responding to a monitoring command, controls the sensor module to monitor the power grid equipment or the area where the power grid is located, and sends the monitoring results to the data service center via the local data communication module.
[0042] It should be noted that the local monitoring subsystem primarily acquires local monitoring data of the power grid equipment or its surrounding area through sensor modules installed on the power grid equipment. The local main control module then uploads this data to the data service center via a local data communication module, thus achieving local monitoring data collection. The local data communication module can be a mobile network communication module, a LoRa communication module combined with a mobile network communication module, or a LoRa communication module combined with a BeiDou communication network. For example, within mobile network range, the local main control module can directly upload local monitoring data to the data service center via mobile networks such as 4G or 5G. Outside mobile network range or in areas with unstable signals, the local monitoring data can be uploaded to a repeater via a LoRa communication module. The repeater then uploads the acquired local monitoring data to the data service center via a mobile communication network or a BeiDou communication network. The local data communication module of the local monitoring subsystem can select the appropriate communication method based on its actual location to achieve local monitoring data transmission. Because power grids cover a wide area, and their equipment and transmission lines are scattered and numerous, the local monitoring subsystem in this invention can be distributed by setting up disaster points within the power grid. That is, a local monitoring subsystem is set up in each corresponding area where a disaster has occurred or is prone to occur, and then this local monitoring subsystem collects data within that corresponding area.
[0043] Data Service Center 102 is used to preprocess local monitoring data, and based on the processed local monitoring data, to predict power grid disasters through feature mining and correlation analysis, and to issue power grid disaster warnings through a preset local early warning model. When a power grid disaster warning is detected in a certain area, the mobile inspection subsystem is triggered, and when a disaster is predicted to occur in a certain location, the satellite monitoring subsystem is triggered.
[0044] Based on a pre-set anomaly monitoring model, disasters are confirmed in areas where power grid disaster warnings may be issued based on video monitoring data; and specific areas where disasters may occur are obtained based on satellite imagery.
[0045] It should be noted that after receiving local monitoring data, the local monitoring data is first preprocessed, including intelligent cleaning and noise reduction. For example, based on the LSTM time series prediction model, the data fluctuation cycle is mined to detect sudden abnormal values of parameters such as temperature, humidity, and current, such as jump data caused by temporary sensor failures. Alternatively, the local monitoring data is uniformly formatted according to the unified data format rules, while removing invalid or interfering data, so that the local monitoring data can be intelligently cleaned and noise reduced.
[0046] Next, after preprocessing the local monitoring data, the data service center will group the local monitoring data according to the type of power grid disaster to obtain multiple sets of local monitoring data. Then, based on each set of local monitoring data, early warning and monitoring of different types of power grid disasters will be achieved. Specifically, deep feature mining and correlation analysis of each set of local monitoring data are used to predict and monitor power grid disasters, thus overcoming the limitations of existing single-dimensional analysis. For example, time-series pattern mining algorithms are used to analyze the time-series correlation of "rainfall - soil moisture - tower tilt" in ground sensors to determine whether there is tower tilt in the power grid. For instance, if it is found that when the rainfall and soil moisture exceed the preset value for several consecutive days, the probability of tower tilt risk will exceed the preset warning threshold within 24 or 48 hours. At this time, the risk of tower tilt can be predicted by setting a warning threshold. Similarly, by constructing the time-series correlation of each power grid disaster, early warning of different types of power grid disasters can be achieved. For instance, by analyzing the time-series correlation of "rainfall - water level - equipment water immersion" in the area where the power grid equipment is located in ground sensors, it is determined whether the power grid equipment is flooded. By monitoring the time and magnitude of rainfall and the continuous changes in water level rise, the degree of equipment flooding can be judged in a timely manner to achieve early warning and monitoring of power grid flooding.
[0047] Simultaneously, historical data is used to construct models for each type of power grid disaster, and deep neural network models are used to construct models for different types of power grid disasters. Local monitoring data related to different types of power grid disasters are integrated to construct datasets, thereby building local early warning models for each type of power grid disaster. When new local monitoring data is collected, it is cleaned, denoised, and grouped as described above, and then input into the corresponding local early warning model to provide local early warnings for power grid disasters.
[0048] Furthermore, when the data service center detects a potential power grid disaster warning in a specific area, it also coordinates the work of the satellite monitoring subsystem and the mobile monitoring subsystem to achieve early warning of power grid disasters from different angles. Specifically, by activating the automatic inspection of drones in the inspection and monitoring subsystem, video images of the corresponding area are inspected, and the obtained video monitoring data is sent back to the data service center. The data service center preprocesses the video monitoring data, extracts keyframes to obtain keyframe images, extracts feature vectors from multiple keyframe images to obtain corresponding feature vectors, and finally matches and compares them with the anomaly monitoring model for that area constructed in the system to determine whether there is an anomaly of a power grid disaster in that area. The anomaly monitoring model refers to the collection of video image data or image data of various power grid disasters that have occurred in the area in history, processing the images to obtain multiple image data, and then extracting feature vectors from each image data to construct the anomaly monitoring model for that area. Similarly, historical video or image data of the area where no power grid disasters have occurred can be collected and processed to obtain multiple image data to derive a normal monitoring model for the area. Then, keyframe images obtained from the real-time video monitoring data are extracted, and feature vectors are extracted and input into the normal monitoring model to determine whether the area is normal. When comparing the keyframe images with the model, the similarity between the keyframe image and the images in the model is calculated using the feature vectors of each image to arrive at the judgment result. For example, when judging with an anomaly monitoring model, if one or more images in the system have a similarity exceeding a certain threshold with the keyframe images, it is considered that an anomaly monitoring model exists in the area. Conversely, when comparing with a normal monitoring model, if no images in the system are identical to multiple keyframe images, it is considered that an anomaly may exist in the area. Specifically, the value of the above threshold can be set based on practical experience.
[0049] For details on identifying specific areas where disasters may occur based on satellite imagery, please refer to the following description of satellite monitoring subsystem 104.
[0050] The mobile inspection subsystem 103 is used to control drones to conduct inspections, obtain video monitoring data of areas where there may be early warnings of power grid disasters, and transmit the data back to the data service center.
[0051] It should be noted that, based on the above explanation of Data Service Center 102, it can be understood that when a temporary inspection task needs to be initiated, the Data Service Center issues the temporary inspection task, enabling the drone inspection base station to control the drone inspection terminal to initiate the temporary inspection based on the task. The temporary inspection task may include data such as inspection time, inspection area, and inspection route. The drone will first inspect the inspection area according to the initial route, and then dynamically adjust the inspection route based on the inspection area range and the cause of any abnormalities. For example, by equipping the drone with an edge AI module, when a wildfire or fire point is detected, the drone can automatically adjust its flight altitude during the inspection and activate the infrared thermal imager to simultaneously acquire data such as the temperature and spread rate of the fire or wildfire, and promptly upload the drone inspection data to the Data Service Center.
[0052] Satellite monitoring subsystem 104 is used to acquire satellite images of locations where power grid disasters may occur and transmit them back to the data service center;
[0053] It should be noted that the satellite monitoring subsystem monitors power grid disasters by acquiring satellite imagery. Specifically, it uses big data mining to analyze historical satellite imagery patterns related to lighting and cloud cover, automatically identifying and removing invalid pixels caused by fog, shadows, etc., to preserve key feature areas in the satellite imagery, such as the location of wildfire hotspots and flooded areas, thus enabling the location of corresponding power grid disasters. For example, by linking the local monitoring subsystem with satellite monitoring, when the data service center analyzes local monitoring data and detects anomalies in a corresponding area, satellite imagery data can be acquired promptly based on the time of the anomaly to further determine the size of the area affected by the power grid disaster. Since the sensors corresponding to the local monitoring data are generally installed in a fixed location, the location or area monitored by the local monitoring subsystem is limited by the sensor's installation location. Therefore, when pre-processed local monitoring data analysis indicates potential flooding or wildfires in a certain location, satellite imagery acquired by the satellite monitoring subsystem can be used to further determine the areas covered by flooding or wildfires, providing more valuable data analysis for rescue efforts.
[0054] The cloud data platform 105 is used to store monitoring data, prediction results, and early warning results collected by the data service center, as well as to store algorithm models used for early warning and prediction.
[0055] It should be noted that the cloud data platform communicates with the data service center. The cloud data platform stores monitoring data collected by the data service center, as well as prediction and early warning results obtained from system analysis, and data from models built within the system. By retaining the data collected and calculated within the system, it facilitates data tracking. Simultaneously, storing data in the cloud data center improves the data processing performance of the data service center, enabling data computation and integration without requiring excessive storage space. Furthermore, it separates data computation from data storage to ensure data security. Data transmission between the cloud data platform and the data service center is encrypted to guarantee secure data transmission.
[0056] In one embodiment, the collaborative system for power grid disaster monitoring and early warning of the present invention further includes: a maintenance work order system;
[0057] The maintenance work order system is used to receive maintenance work orders, real-time monitoring data of the maintenance area where the maintenance work order is located, and disaster emergency response model, and send them to the terminals carried by the staff. This allows the staff to carry out maintenance on the maintenance area based on the maintenance work order, real-time monitoring data, and disaster emergency response model, and return the maintenance results to the data service center. The maintenance work order, real-time monitoring data, and disaster emergency response model are issued by the data service center, and the maintenance work order is generated based on power grid disaster early warning.
[0058] It should be noted that the data service center, through its connection with the maintenance work order system, promptly generates corresponding maintenance work orders based on early warning notifications and issues these work orders to the system in a timely manner, while also receiving feedback on the maintenance work order system's repair results. While staff are performing maintenance on these work orders, the data service center also sends real-time monitoring data of the corresponding maintenance area to the maintenance work order system, such as real-time local monitoring data: temperature and humidity, the operational status of power grid equipment, and water immersion status. Simultaneously, based on real-time local monitoring data, the data service center estimates the on-site work hazard level and promptly sends this information to the staff's terminals via the maintenance work order system, alerting them to take appropriate measures for maintenance. Furthermore, when generating maintenance work orders, the data service center also uses a disaster emergency response model to customize an emergency plan for each work order and pushes it to the maintenance work order system for reference by repair personnel. By collecting real-time maintenance plans from similar historical work orders, the data service center uses big data mining and other methods to provide recommended emergency plans for the current work order.
[0059] Furthermore, the data service center can also support natural language queries by building a power grid disaster operation and maintenance knowledge base. When repair personnel access the maintenance work order system through their terminal devices, they can submit relevant questions through the question-and-answer page provided by the system. The maintenance work order system then feeds back the questions to the data service center, which analyzes the questions and provides answers based on the power grid disaster operation and maintenance knowledge base. Specifically, the power grid disaster operation and maintenance knowledge base includes various preset questions and answers, which are periodically synchronized to the maintenance work order system for rapid response. If a question submitted by a staff member is not found in the maintenance work order system, the question is forwarded to the data service center, which analyzes the new question and provides an answer based on the power grid disaster operation and maintenance knowledge base.
[0060] Furthermore, it is understandable that the data service center promptly uploads maintenance work orders and maintenance results, as well as the aforementioned local monitoring data, prediction results, and early warning results, to the cloud data platform for storage, thereby reducing the data storage pressure on the data service center and ensuring unified storage and security.
[0061] In one embodiment, the collaborative system for power grid disaster monitoring and early warning of the present invention further includes: a third-party interface for accessing a third-party system, so that the third-party system, after responding to the early warning command, issues an early warning for power grid disaster based on real-time monitoring data and returns the early warning result.
[0062] It should be noted that the collaborative system for power grid disaster monitoring and early warning of the present invention also includes a third-party interface for accessing third-party systems, such as meteorological data from meteorological stations, to achieve early warning of power grid disasters. Specifically, an entity layer can be constructed, including core entities such as transmission lines, towers, meteorological stations, and disaster points. An entity-relationship graph can be built based on a graph neural network, for example, by using big data mining to obtain historical disaster cases to define causal relationships such as "meteorological conditions - disaster occurrence - equipment damage". When new monitoring data is acquired, the entity-relationship graph built based on the graph neural network is used to match similar historical scenarios to output risk propagation paths, such as heavy rainfall - excessive rainfall, increased soil moisture - equipment tilting or waterlogging - regional power outage, thereby achieving early warning analysis of regional power outages and providing visualized data for early prevention and control. That is, different entities are obtained through data mining, and relationships are built between multiple entities to form a graph, thereby realizing the correlation mining of multi-source data and the mining of wind direction propagation paths. The specific implementation can be carried out by the currently common graph construction method, and the third-party system returns the early warning results to the collaborative system for power grid disaster monitoring and early warning of this invention. This embodiment realizes the early warning of power grid disasters through the above basic principles.
[0063] In one embodiment, the mobile inspection subsystem 103 is further configured to: after responding to a timed inspection command, control the drone to perform inspections along a preset route according to a preset inspection cycle, and upload the inspection data to the data service center, so that the data service center can perform anomaly monitoring based on the inspection data obtained from the timed inspections.
[0064] It should be noted that, in addition to the inspections triggered by the data service center, the mobile inspection subsystem also performs scheduled inspections under the control of the collaborative system (i.e., after responding to scheduled inspection commands). This allows the data service center to upload the inspection data to the data service center, enabling it to monitor anomalies within the region using the model matching method described above. For example, regular drone inspections can detect anomalies in vegetation cover on power grid equipment within a given area. The data service center can then promptly generate early warning notifications for relevant maintenance departments, thus achieving anomaly monitoring for power grid disasters. The mobile inspection subsystem includes a drone inspection base station and a drone inspection terminal. Data communication between the drone inspection subsystem and the data service center is achieved through the main control module and communication module of the drone inspection base station, receiving inspection tasks and acquiring drone inspection data obtained from these tasks. Furthermore, the drone inspection route is generally a system-preset route. The main control module of the drone inspection base station periodically initiates inspection tasks to control the drone inspection terminal to perform regular inspections along the predetermined route.
[0065] In one embodiment, the satellite monitoring subsystem is further configured to: upon responding to an anomaly monitoring command, perform a similarity matching comparison between real-time satellite images of the environment in which the power grid to be monitored is located and historical satellite images, and determine whether there is an anomaly in the environment in which the area to be monitored is located based on the comparison results.
[0066] And when there is an anomaly in the environment of the area to be inspected, the mobile inspection subsystem is triggered, so that the mobile inspection subsystem controls the drone to inspect the area to be inspected.
[0067] It should be noted that, in addition to the satellite images uploaded and acquired after being triggered by the data service center, the satellite monitoring subsystem can also determine whether any anomalies have occurred in the area where the power grid is located based on historical satellite images. Specifically, by matching and comparing the real-time acquired satellite images with historically acquired satellite images, the similarity between the currently acquired satellite images and historically acquired satellite images is determined to identify the changed parts in the currently acquired satellite images. This is then combined with historical satellite image data to analyze the changing trends of the changed areas. For example, over time, vegetation cover density increases. By analyzing the changing trends of the area or density of vegetation cover in continuously acquired satellite images, it is possible to determine whether there are any anomalies in the vegetation cover. Furthermore, by considering the area where the power grid is located, it is possible to determine whether there are any anomalies in the vegetation cover of the area where the power grid is located.
[0068] Furthermore, when abnormal vegetation cover is detected, the drone inspection subsystem can be linked and controlled to inspect the corresponding area, further determining whether there are vegetation anomalies in the power grid area. In other words, this invention uses a satellite monitoring subsystem, a mobile inspection subsystem, and a local monitoring subsystem to detect and warn of power grid disasters in the power grid area. It can also link and control multiple subsystems within these systems to further determine abnormal results in the power grid area. This addresses the problems of existing methods that rely on a single system or single-dimensional factor to assess power grid disasters, which may result in untimely or inaccurate monitoring results, hindering timely technical warnings and potentially leading to power grid failures and losses.
[0069] This invention provides a collaborative system for power grid disaster monitoring and early warning. On one hand, it utilizes coordinated air, space, and ground monitoring to achieve early warning of power grid disasters, addressing the problem of untimely monitoring caused by relying on single data thresholds. Simultaneously, this invention leverages big data mining and modeling to integrate multi-source data for comprehensive early warning of power grid disasters, improving the accuracy of monitoring and early warning, making monitoring more timely, and achieving early warning. Furthermore, it integrates with a maintenance work order system to enable the issuance and feedback of maintenance work orders; and it constructs a power grid disaster operation and maintenance knowledge base to enable intelligent operation and maintenance questioning, helping repair personnel quickly find operation and maintenance knowledge for rapid repairs. On the other hand, it includes a third-party interface, connecting to a meteorological workstation to obtain meteorological data, thus diversifying the data source for power grid disaster monitoring. This invention solves the problems of existing monitoring methods being singular and lacking coordination, as well as insufficient data analysis depth, leading to low accuracy and timeliness of early warnings.
[0070] The above describes a collaborative system for power grid disaster monitoring and early warning provided in an embodiment of the present invention. The following describes a collaborative method for power grid disaster monitoring and early warning provided in an embodiment of the present invention.
[0071] Please see Figure 2 The present invention provides a collaborative method for power grid disaster monitoring and early warning, comprising:
[0072] Step 201: Obtain local monitoring data of the area where the power grid equipment is located, and preprocess the local monitoring data.
[0073] Step 202: Based on the processed local monitoring data, perform power grid disaster prediction through feature mining and correlation analysis, and perform power grid disaster early warning through a preset local early warning model. When a power grid disaster early warning is detected in a certain area, proceed to step 203. When a disaster is predicted to occur in a certain location, proceed to step 204.
[0074] Step 203: Use drones to conduct inspections and obtain video monitoring data of areas where there may be power grid disaster warnings. Based on the preset anomaly monitoring model, confirm the disaster in areas where there may be power grid disaster warnings according to the video monitoring data.
[0075] Step 204: Obtain satellite images of locations where power grid disasters may occur, and identify specific areas where disasters may occur based on the satellite images.
[0076] Furthermore, this embodiment of the invention also provides a collaborative device for power grid disaster monitoring and early warning, the device including a processor and a memory:
[0077] The memory is used to store program code and transmit the program code to the processor;
[0078] The processor is used to execute the steps of the collaborative method for power grid disaster monitoring and early warning as described in the above method embodiments, according to the instructions in the program code.
[0079] Furthermore, this embodiment of the invention also provides a computer-readable storage medium for storing program code, which is used to execute the collaborative method for power grid disaster monitoring and early warning described in the above method embodiments.
[0080] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the method described above can be referred to the corresponding process in the aforementioned system embodiments, and will not be repeated here.
[0081] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.
[0082] The units described as separate components may or may not be physically separate. 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 units can be selected to achieve the purpose of this embodiment according to actual needs.
[0083] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0084] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0085] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A collaborative system for power grid disaster monitoring and early warning, characterized in that, include: The local monitoring subsystem is used to acquire local monitoring data of the area where the power grid equipment is located and send it to the data service center; The data service center is used to preprocess the local monitoring data, and based on the processed local monitoring data, to predict power grid disasters through feature mining and correlation analysis, and to issue power grid disaster warnings through a preset local early warning model. When a power grid disaster warning is detected in a certain area, the mobile inspection subsystem is triggered, and when a disaster is predicted to occur in a certain location, the satellite monitoring subsystem is triggered. Based on a pre-set anomaly monitoring model, disaster confirmation is performed on areas where power grid disaster warnings may be issued based on video monitoring data; and specific areas where disasters may occur are obtained based on satellite imagery. The mobile inspection subsystem is used to control drones to conduct inspections, obtain video monitoring data of areas where there may be early warnings of power grid disasters, and transmit the data back to the data service center. The satellite monitoring subsystem is used to acquire satellite images of locations where power grid disasters may occur and transmit them back to the data service center; The cloud-based data platform is used to store monitoring data, prediction results, and early warning results collected by the data service center, as well as the algorithm models used for early warning and prediction.
2. The collaborative system for power grid disaster monitoring and early warning according to claim 1, characterized in that, Also includes: Repair work order system; The maintenance work order system is used to receive maintenance work orders, real-time monitoring data of the maintenance area where the maintenance work order is located, and disaster emergency response model, and send them to the terminal carried by the staff, so that the staff can perform maintenance on the maintenance area according to the maintenance work order, the real-time monitoring data, and the disaster emergency response model and return the maintenance results to the data service center; The maintenance work order, the real-time monitoring data, and the disaster emergency response model are issued by the data service center, and the maintenance work order is generated based on power grid disaster early warning.
3. The collaborative system for power grid disaster monitoring and early warning according to claim 1, characterized in that, Also includes: Third-party interfaces are used to connect to third-party systems, enabling these systems to issue early warnings about power grid disasters based on real-time monitoring data and return the warning results after responding to early warning commands.
4. The collaborative system for power grid disaster monitoring and early warning according to claim 1, characterized in that, The mobile inspection subsystem is also used to: after responding to a timed inspection command, control the drone to perform inspections along a preset route according to a preset inspection cycle, and upload the inspection data to the data service center, so that the data service center can perform anomaly monitoring based on the inspection data obtained from the timed inspections.
5. The collaborative system for power grid disaster monitoring and early warning according to claim 1, characterized in that, The satellite monitoring subsystem is also used to: after responding to an anomaly monitoring command, perform similarity matching and comparison between real-time satellite images of the environment of the power grid to be monitored area and historical satellite images, and determine whether there is an anomaly in the environment of the area to be monitored based on the comparison results.
6. The collaborative system for power grid disaster monitoring and early warning according to claim 1, characterized in that, The satellite monitoring subsystem is also used to: trigger the mobile inspection subsystem when there is an anomaly in the environment of the area to be inspected, so that the mobile inspection subsystem controls the drone to inspect the area to be inspected.
7. The collaborative system for power grid disaster monitoring and early warning according to claim 1, characterized in that, The local monitoring subsystem specifically includes: a sensor module, a local main control module, and a local data communication module; wherein, the sensor module is installed in the power grid equipment or the area where the power grid is located; The local master control module is used to control the sensor module to monitor the power grid equipment or the area where the power grid is located after responding to the monitoring command, and to send the monitoring results to the data service center through the local data communication module.
8. A collaborative method for power grid disaster monitoring and early warning, characterized in that, include: S1. Obtain local monitoring data of the area where the power grid equipment is located, and preprocess the local monitoring data; S2. Based on the processed local monitoring data, power grid disaster prediction is performed through feature mining and correlation analysis, and power grid disaster early warning is performed through a preset local early warning model. When a power grid disaster early warning is detected in a certain area, step S3 is executed. When a disaster is predicted to occur in a certain location, step S4 is executed. S3. Use drones to conduct inspections and obtain video monitoring data of areas where there may be power grid disaster warnings. Based on a preset anomaly monitoring model, confirm the disaster in the areas where there may be power grid disaster warnings according to the video monitoring data. S4. Obtain satellite images of locations where power grid disasters may occur, and obtain specific areas where disasters may occur based on the satellite images.
9. A collaborative device for power grid disaster monitoring and early warning, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the collaborative method for power grid disaster monitoring and early warning as described in claim 8 according to the instructions in the program code.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code for executing the collaborative method for power grid disaster monitoring and early warning as described in claim 8.