Unmanned aerial vehicle inspection method based on strong earthquake monitoring system and related device

Abstract

The present disclosure provides a kind of unmanned aerial vehicle inspection method based on strong earthquake monitoring system and related device, it is related to computer technology field.The method is: according to the associated data of target hydropower station and geological disaster evaluation model, the disaster area information of target hydropower station is determined;Disaster area information includes the safety early warning threshold of each disaster index of each risk area in target hydropower station;Real-time monitoring value of strong earthquake monitoring system is obtained, and real-time monitoring value and safety early warning threshold in disaster area information are compared, and first comparison result is obtained;When determining that first comparison result first sub-comparison result indicates abnormality, control unmanned aerial vehicle to the abnormal level risk area corresponding to first sub-comparison result is inspected, and obtains the inspection measured data;Comparison is carried out between inspection measured data and associated data, and second comparison result is obtained, and according to second comparison result, the prevention and control strategy for abnormal level risk area is generated.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a method, apparatus, electronic equipment and program product for unmanned aerial vehicle (UAV) inspection based on a strong earthquake monitoring system. Background Technology

[0002] As safety and security requirements for hydropower stations continue to be upgraded, geological disasters in reservoir areas triggered by strong earthquakes have become a core risk factor threatening the safety of the projects and the surrounding ecology. Hydropower station reservoirs are mostly located in deep mountain valleys with complex terrain and fragile geological conditions. Strong earthquakes can easily trigger a chain of disasters such as landslides, rockfalls, and mudslides, potentially leading to serious consequences such as dam damage, reservoir bank instability, and power transmission line interruptions, directly impacting the normal operation of the hydropower station and the safety of life and property downstream.

[0003] However, there is a significant disconnect between earthquake monitoring and disaster inspection in the reservoir area, making it difficult to meet the needs of rapid post-earthquake prevention and control.

[0004] On the one hand, although strong earthquake monitoring systems can collect data such as earthquake intensity, slope deformation, and structural vibration in real time through ground sensor networks and issue alarms, they can only provide abstract data indicators and cannot intuitively present the actual disaster situation in the earthquake zone, resulting in a lack of concrete basis for command and decision-making. On the other hand, the traditional manual inspection mode is slow to respond, and it often takes several hours to organize personnel to enter the site after an earthquake. In addition, there are many blind spots in the reservoir area, such as steep slopes, densely vegetated areas, and collapse hazard zones, which are difficult for manual inspection to reach. At the same time, it is impossible to accurately identify potential hazards such as hidden cracks under vegetation cover and shallow soil slippage, which greatly restricts the timeliness and comprehensiveness of disaster prevention and control. Summary of the Invention

[0005] In view of this, this disclosure provides a drone inspection method based on a strong earthquake monitoring system, a drone inspection device based on a strong earthquake monitoring system, electronic equipment and computer program products, so as to improve the disaster prevention and control effect of hydropower stations to a certain extent.

[0006] According to a first aspect of this disclosure, a method for unmanned aerial vehicle (UAV) inspection based on a strong earthquake monitoring system is provided, the method comprising: Based on the associated data of the target hydropower station and the geological disaster assessment model, the disaster area information of the target hydropower station is determined; the disaster area information includes the safety warning thresholds of various disaster indicators for each level of risk area within the target hydropower station; The real-time monitoring values ​​of the strong earthquake monitoring system are obtained, and the real-time monitoring values ​​are compared with the safety warning thresholds in the disaster area information to obtain a first comparison result; When it is determined that the first sub-comparison result in the first comparison result indicates an anomaly, the drone is controlled to inspect the risk area corresponding to the anomaly level of the first sub-comparison result and obtain the actual inspection data. The actual inspection data is compared with the associated data to obtain a second comparison result, and a prevention and control strategy for the abnormal risk area is generated based on the second comparison result.

[0007] In one possible implementation, the disaster area information of the target hydropower station is determined based on the associated data and geological disaster assessment model, including: Collect topographic and geomorphological data, geological and soil characteristics data, strong earthquake site monitoring basic data, static benchmark deformation data, reservoir area hydrological environment data, and hydropower project disturbance construction data of the target hydropower station as associated data for the target hydropower station; The various indicator data of the associated data are transformed into dimensionless data to obtain a first dataset; wherein, the first dataset contains standardized indicator scores of the grid cells of the target hydropower station; Based on the weighted evaluation rules for geological hazard susceptibility and the first dataset, the comprehensive evaluation value of geological hazard susceptibility is calculated for each grid cell to obtain the second dataset; The second dataset and the disaster risk level division intervals are matched to determine the disaster susceptibility level of each grid cell; Based on the disaster susceptibility level of each grid cell, the vector boundary coordinates, main disaster-causing factors, and safety warning thresholds of various disaster indicators of each level of risk area within the target hydropower station are determined to identify the disaster area information of the target hydropower station.

[0008] In one possible implementation, the weighted evaluation rule for geological hazard susceptibility is determined based on the following method: Based on the aforementioned associated data, a three-level evaluation index system is established, and based on the three-level evaluation index system, a hierarchical index list is determined; wherein, the three-level evaluation index system sets the target layer as the comprehensive evaluation of the geological hazard susceptibility of hydropower stations from top to bottom, the criterion layer is divided into geological basic conditions, strong earthquake disturbance conditions, hydrological permeability conditions and engineering disturbance conditions, and the index layer is the subdivided disaster-causing factors under each criterion dimension. Based on the hierarchical index list, construct pairwise comparison judgment matrices between each index under the criterion layer to obtain multiple sets of initial judgment matrices. Consistency verification is performed on the multiple sets of initial judgment matrices to obtain qualified judgment matrices, and the index weight coefficients are solved based on the qualified judgment matrices to determine the weighted evaluation rules for geological hazard susceptibility.

[0009] In one possible implementation, the disaster area information of the target hydropower station is determined based on the associated data and geological disaster assessment model, including: Collect topographic and geomorphological data, geological and soil characteristics data, strong earthquake site monitoring basic data, static benchmark deformation data, reservoir area hydrological environment data, and hydropower project disturbance construction data of the target hydropower station as associated data for the target hydropower station; The associated data is divided to determine positive stable indicators and negative hazard indicators. The positive stable indicators and negative hazard indicators are then normalized using the range standardization method to obtain a standardized disaster-causing factor sequence with unified dimensions. Based on the critical thresholds of various disasters corresponding to the target hydropower station, a critical standard reference sequence for disaster outbreak is established; Calculate the grey relational coefficient between the critical standard reference sequence for disaster outbreak and the standardized disaster-causing factor sequence, and construct a grey relational degree matrix of disaster risks for the entire grid unit. Based on the gray relational degree matrix of the disaster hazard and the weight coefficients of all disaster-causing factors, a gray relational degree result set is determined; and based on the gray relational degree result set and the preset mapping relationship, the disaster area information of the target hydropower station is determined; wherein, the weight coefficients of all disaster-causing factors are determined based on the entropy weight algorithm and the standardized disaster-causing factor sequence.

[0010] In one possible implementation, comparing the real-time monitoring value with the safety warning threshold within the disaster area information to obtain a first comparison result includes: The strong ground motion intensity observation data within the real-time monitoring values ​​are compared with the strong ground motion intensity safety warning threshold within the disaster area information to obtain a first comparison result; or, Based on the comparison results of the strong ground motion intensity observation data within the real-time monitoring values ​​and the strong ground motion intensity safety warning threshold within the disaster area information, and the comparison results of the three-dimensional displacement data within the real-time monitoring values ​​and the displacement warning threshold within the disaster area information, a first comparison result is determined.

[0011] In one possible implementation, when it is determined that the first sub-comparison result in the first comparison result indicates an anomaly, the drone is controlled to inspect the anomaly level risk area corresponding to the first sub-comparison result, and the inspection measurement data is obtained, including: Generate inspection tasks for the aforementioned abnormal risk areas; wherein the parameters of the inspection tasks include the UAV take-off and landing coordinates, the operation and inspection altitude, the image shooting angle, and the aerial survey sampling density; Control the drone to perform the inspection task and obtain the actual inspection data.

[0012] In one possible implementation, comparing the actual inspection data with the associated data to obtain a second comparison result includes: The measured elevation data in the inspection data and the benchmark deformation data in the associated data are compared to obtain the terrain comparison result; wherein, the terrain comparison result is used to indicate whether the anomaly level risk area has subsidence, uplift, or soil slippage. The real-scene image data within the inspection and measurement data is processed for feature recognition to obtain post-disaster features; and the topographic data within the associated data is processed for feature recognition to obtain baseline distribution features, and the post-disaster features and the baseline distribution features are compared to obtain distribution comparison results. Based on the terrain comparison results and distribution comparison results, a second comparison result is determined.

[0013] According to a second aspect of this disclosure, a drone inspection device based on a strong earthquake monitoring system is provided, the device comprising: The first processing unit is used to determine the disaster area information of the target hydropower station based on the associated data and geological disaster assessment model; the disaster area information includes the safety warning thresholds of various disaster indicators for each level of risk area within the target hydropower station; The comparison unit is used to obtain the real-time monitoring value of the strong earthquake monitoring system and compare the real-time monitoring value with the safety warning threshold in the disaster area information to obtain the first comparison result; The inspection unit is used to control the drone to inspect the risk area corresponding to the abnormal level of the first sub-comparison result when it is determined that the first sub-comparison result in the first comparison result indicates an abnormality, and to obtain the actual inspection data. The second processing unit is used to compare the actual inspection data with the associated data to obtain a second comparison result, and generate a prevention and control strategy for the abnormal level risk area based on the second comparison result.

[0014] In one possible implementation, the first processing unit is configured to: Collect topographic and geomorphological data, geological and soil characteristics data, strong earthquake site monitoring basic data, static benchmark deformation data, reservoir area hydrological environment data, and hydropower project disturbance construction data of the target hydropower station as associated data for the target hydropower station; The various indicator data of the associated data are transformed into dimensionless data to obtain a first dataset; wherein, the first dataset contains standardized indicator scores of the grid cells of the target hydropower station; Based on the weighted evaluation rules for geological hazard susceptibility and the first dataset, the comprehensive evaluation value of geological hazard susceptibility is calculated for each grid cell to obtain the second dataset; The second dataset and the disaster risk level division intervals are matched to determine the disaster susceptibility level of each grid cell; Based on the disaster susceptibility level of each grid cell, the vector boundary coordinates, main disaster-causing factors, and safety warning thresholds of various disaster indicators of each level of risk area within the target hydropower station are determined to identify the disaster area information of the target hydropower station.

[0015] In one possible implementation, the weighted evaluation rule for geological hazard susceptibility is determined based on the following method: Based on the aforementioned associated data, a three-level evaluation index system is established, and based on the three-level evaluation index system, a hierarchical index list is determined; wherein, the three-level evaluation index system sets the target layer as the comprehensive evaluation of the geological hazard susceptibility of hydropower stations from top to bottom, the criterion layer is divided into geological basic conditions, strong earthquake disturbance conditions, hydrological permeability conditions and engineering disturbance conditions, and the index layer is the subdivided disaster-causing factors under each criterion dimension. Based on the hierarchical index list, construct pairwise comparison judgment matrices between each index under the criterion layer to obtain multiple sets of initial judgment matrices. Consistency verification is performed on the multiple sets of initial judgment matrices to obtain qualified judgment matrices, and the index weight coefficients are solved based on the qualified judgment matrices to determine the weighted evaluation rules for geological hazard susceptibility.

[0016] In one possible implementation, the first processing unit is configured to: Collect topographic and geomorphological data, geological and soil characteristics data, strong earthquake site monitoring basic data, static benchmark deformation data, reservoir area hydrological environment data, and hydropower project disturbance construction data of the target hydropower station as associated data for the target hydropower station; The associated data is divided to determine positive stable indicators and negative hazard indicators. The positive stable indicators and negative hazard indicators are then normalized using the range standardization method to obtain a standardized disaster-causing factor sequence with unified dimensions. Based on the critical thresholds of various disasters corresponding to the target hydropower station, a critical standard reference sequence for disaster outbreak is established; Calculate the grey relational coefficient between the critical standard reference sequence for disaster outbreak and the standardized disaster-causing factor sequence, and construct a grey relational degree matrix of disaster risks for the entire grid unit. Based on the gray relational degree matrix of the disaster hazard and the weight coefficients of all disaster-causing factors, a gray relational degree result set is determined; and based on the gray relational degree result set and the preset mapping relationship, the disaster area information of the target hydropower station is determined; wherein, the weight coefficients of all disaster-causing factors are determined based on the entropy weight algorithm and the standardized disaster-causing factor sequence.

[0017] In one possible implementation, the comparison unit is used for: The strong ground motion intensity observation data within the real-time monitoring values ​​are compared with the strong ground motion intensity safety warning threshold within the disaster area information to obtain a first comparison result; or, Based on the comparison results of the strong ground motion intensity observation data within the real-time monitoring values ​​and the strong ground motion intensity safety warning threshold within the disaster area information, and the comparison results of the three-dimensional displacement data within the real-time monitoring values ​​and the displacement warning threshold within the disaster area information, a first comparison result is determined.

[0018] In one possible implementation, the inspection unit is used for: Generate inspection tasks for the aforementioned abnormal risk areas; wherein the parameters of the inspection tasks include the UAV take-off and landing coordinates, the operation and inspection altitude, the image shooting angle, and the aerial survey sampling density; Control the drone to perform the inspection task and obtain the actual inspection data.

[0019] In one possible implementation, the second processing unit is configured to: The measured elevation data in the inspection data and the benchmark deformation data in the associated data are compared to obtain the terrain comparison result; wherein, the terrain comparison result is used to indicate whether the anomaly level risk area has subsidence, uplift, or soil slippage. The real-scene image data within the inspection and measurement data is processed for feature recognition to obtain post-disaster features; and the topographic data within the associated data is processed for feature recognition to obtain baseline distribution features, and the post-disaster features and the baseline distribution features are compared to obtain distribution comparison results. Based on the terrain comparison results and distribution comparison results, a second comparison result is determined.

[0020] According to a third aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method of the first aspect described above and possible implementations thereof.

[0021] According to a fourth aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of the first aspect and possible implementations thereof by executing the executable instructions.

[0022] The technical solution disclosed herein has the following beneficial effects: In this embodiment, the disaster area information of the target hydropower station can be determined based on the associated data and geological disaster assessment model. The disaster area information includes the safety warning thresholds of various disaster indicators for each risk level within the target hydropower station. In other words, this disclosure builds a geological disaster assessment model based on multi-source initial basic data of the target hydropower station, which can accurately classify disaster-prone areas across the entire region and clearly define the high, medium, and low risk control areas in advance. Compared with the traditional aimless blind inspection mode, this allows subsequent drone inspection operations to accurately focus on high-risk areas, improving the targeting and efficiency of inspection operations from the source, and realizing the transformation of geological disasters from post-disaster handling to pre-disaster prediction and control.

[0023] In this embodiment of the disclosure, real-time monitoring values ​​of a strong earthquake monitoring system can be obtained, and the real-time monitoring values ​​can be compared with safety warning thresholds within disaster area information to obtain a first comparison result; when it is determined that the first sub-comparison result in the first comparison result indicates an anomaly, the drone is controlled to inspect the anomaly-level risk area corresponding to the first sub-comparison result to obtain inspection measurement data; and the inspection measurement data is compared with associated data to obtain a second comparison result, and a prevention and control strategy for the anomaly-level risk area is generated based on the second comparison result.

[0024] As can be seen, this invention integrates a strong earthquake monitoring system to collect core data such as seismic intensity in the affected area, automatically comparing the data with preset safety warning thresholds without manual intervention. In the event of abnormal conditions such as earthquake disturbances, slope slippage, or dam deformation, it can quickly determine the anomaly and automatically control drones for inspection, eliminating the lag in manual detection and significantly shortening the response time for on-site investigations after a disaster. Furthermore, the automatic drone inspection after a hazard is triggered eliminates the need for personnel to enter high-risk disaster sites such as landslides and rockfalls for on-site investigations, completely avoiding personal safety hazards caused by rockfalls and secondary landslides in mountainous disaster areas. It also overcomes the limitations of manual inspections due to terrain, weather, and nighttime conditions, expanding the operational scenarios for data collection at disaster sites. Furthermore, the rapid analysis of real-time inspection data and related data obtained by drones after the earthquake allows for the precise identification of potential hazards around the disaster site, prediction of secondary geological disaster risks such as landslides and bank collapses induced by aftershocks, and generation of prevention and control strategies that are easy for operation and maintenance management units to manage. This comprehensively strengthens the overall disaster prevention, mitigation, and safe operation guarantee capabilities of the target hydropower station reservoir area and dam area, thereby improving the disaster prevention and control effect of the hydropower station.

[0025] Other features and advantages of this disclosure will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the disclosure. The objects and other advantages of this disclosure may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0026] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments of this disclosure will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This illustration shows a schematic diagram of an application scenario in this exemplary embodiment; Figure 2 This diagram illustrates a geological disaster prevention and control system according to an exemplary embodiment. Figure 3 This illustration shows a flowchart of a drone inspection method based on a strong earthquake monitoring system in this exemplary embodiment. Figure 4 This diagram illustrates the structure of a drone inspection device based on a strong earthquake monitoring system in this exemplary embodiment. Figure 5 A schematic diagram of the structure of an electronic device in this exemplary embodiment is shown. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this disclosure clearer, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure. Unless otherwise specified, the embodiments and features in the embodiments of this disclosure can be arbitrarily combined with each other. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0029] The term "comprising" and any variations thereof in this disclosure and claims are intended to cover non-exclusive protection. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0030] In this disclosure, there are one or more embodiments; "multiple" refers to two or more. "And / or" describes the relationship between the associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following associated objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0031] It should be noted that the terms "first," "second," "third," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order, sequence, size, or priority. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0032] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, which are schematic illustrations of this disclosure and are not necessarily drawn to scale. Some block diagrams shown in the drawings may be functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in hardware modules or integrated circuits, or in networks, processors, or microcontrollers. Implementations can be carried out in various forms and should not be construed as limited to the examples set forth herein. The features, structures, or characteristics described in this disclosure can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough description of embodiments of this disclosure. However, those skilled in the art will recognize that one or more specific details may be omitted when implementing the technical solutions of this disclosure, or other methods, components, apparatuses, steps, etc., may be used to replace one or more specific details.

[0033] It should be noted that certain software, components, models, and other existing industry solutions may be mentioned in the embodiments disclosed herein. These should be considered exemplary and intended only to illustrate the feasibility of implementing the technical solutions disclosed herein, but do not imply that the applicant has already used or necessarily used such solutions. The collection, dissemination, and use of data in the technical solutions disclosed herein all comply with relevant national laws and regulations.

[0034] Currently, the traditional disaster management model based on regular manual inspections can no longer meet the disaster prevention and control needs of hydropower stations.

[0035] In view of this, the exemplary embodiments of this disclosure provide a drone inspection method based on a strong earthquake monitoring system. This method can determine the disaster area information of a target hydropower station based on associated data and a geological disaster assessment model. The disaster area information includes the safety warning thresholds for various disaster indicators in risk areas of different levels within the target hydropower station. In other words, this disclosure builds a geological disaster assessment model based on multi-source initial basic data of the target hydropower station, which can accurately classify disaster-prone areas across the entire region and clearly define high, medium, and low-risk control areas in advance. Compared to the traditional aimless blind inspection mode, this allows subsequent drone inspection operations to accurately focus on high-risk areas, improving the targeting and efficiency of inspection operations from the source, and realizing the transformation of geological disaster response from post-disaster handling to pre-disaster prediction and control.

[0036] In the embodiments of the present disclosure, real-time monitoring values of a strong earthquake monitoring system can be obtained, and the real-time monitoring values are compared with the safety early warning thresholds in disaster area information to obtain a first comparison result; when it is determined that a first sub-comparison result in the first comparison result indicates an abnormality, an unmanned aerial vehicle is controlled to perform inspection on an abnormal-level risk area corresponding to the first sub-comparison result, and actual inspection data is obtained; and the actual inspection data is compared with associated data to obtain a second comparison result, and a prevention and control strategy for the abnormal-level risk area is generated according to the second comparison result.

[0037] It can be seen that the present disclosure integrates a strong earthquake monitoring system to collect core data such as the seismic intensity of the site, which can automatically compare with preset safety early warning thresholds without manual on-duty; once abnormal conditions such as seismic disturbance, slope slip, and dam deformation occur, abnormal changes can be quickly determined and the unmanned aerial vehicle can be automatically controlled to inspect, which eliminates the lag of manual hazard detection and greatly shortens the on-site investigation response time after a disaster occurs. In addition, after a hazard is triggered, the unmanned aerial vehicle is automatically controlled to perform inspection, which does not require staff to enter high-risk disaster sites such as landslides and dangerous rock collapses for field investigation, completely avoiding personal safety hazards caused by rockfall and secondary landslides in mountain disaster sites. At the same time, it can break through manual inspection restrictions such as terrain, weather and night environment, and expand the operation scenarios of data collection at disaster sites. Furthermore, after the unmanned aerial vehicle quickly conducts a full-area inspection after an earthquake, the obtained real-time inspection data and associated data are analyzed, which can accurately screen out derived hidden hazard points around the disaster, predict the risk of secondary geological disasters such as secondary landslides and bank slope collapses induced by aftershocks, and generate prevention and control strategies convenient for operation and management units to manage, so as to comprehensively strengthen the overall disaster prevention, mitigation and safe operation guarantee capabilities of the target hydropower station reservoir area and dam area, and further improve the disaster prevention and control effect for the hydropower station.

[0038] For a better understanding of the technical solutions provided by the embodiments of the present disclosure, the following briefly introduces the application scenarios to which the technical solutions provided by the embodiments of the present disclosure are applicable. It should be noted that the application scenarios described below are only used to illustrate the embodiments of the present disclosure rather than limit them. In specific implementation, the technical solutions provided by the embodiments of the present disclosure can be flexibly applied according to actual needs.

[0039] Please refer to Figure 1 , shown in Figure 1 it is an application scenario to which the technical solution of the embodiments of the present disclosure can be applied. The scenario schematic diagram includes a plurality of acquisition devices 110 and a service device 120. Between the acquisition devices 110 and the service device 120, direct or indirect communication connection can be established through one or more networks 130. Optionally, the application scenario may further include an execution device, and the execution device may perform linkage processing based on the output result of the service device 120, for example, which is not limited in the embodiments of the present disclosure.

[0040] In this embodiment of the disclosure, the data acquisition device 110 can acquire data from multiple sources. In other words, the data acquisition device 110 may include drones, strong earthquake monitoring systems, sensors / terminals in a Global Navigation Satellite System (GNSS), and other data acquisition devices.

[0041] In this embodiment, the data acquisition device 110 can send the acquired associated data of the target hydropower station to the service device 120. Then, the service device 120 can determine the disaster area information of the target hydropower station based on the associated data and the geological disaster evaluation model. The disaster area information includes the safety warning thresholds of various disaster indicators for each level of risk area within the target hydropower station. The service device 120 acquires the real-time monitoring values ​​of the strong earthquake monitoring system and compares the real-time monitoring values ​​with the safety warning thresholds within the disaster area information to obtain a first comparison result. When it is determined that the first sub-comparison result in the first comparison result indicates an anomaly, the service device 120 controls the drone to inspect the abnormal level risk area corresponding to the first sub-comparison result and obtains the inspection measurement data. The service device 120 compares the inspection measurement data with the associated data to obtain a second comparison result and generates a prevention and control strategy for the abnormal level risk area based on the second comparison result.

[0042] In this embodiment of the disclosure, the service device 120 can be a server. The server can be a cloud server or cloud server cluster that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms, but is not limited to this.

[0043] Of course, the methods provided in this disclosure are not limited to... Figure 1 The application scenarios shown can also be used in other possible application scenarios, and this disclosure does not limit the scope of the embodiments.

[0044] In this disclosure embodiment, see Figure 2 The diagram shown is a schematic representation of a geological disaster prevention and control system provided in an embodiment of this disclosure. In this embodiment, the geological disaster prevention and control system includes a data acquisition module, a processing module, an inspection module, and an early warning module.

[0045] In this embodiment of the disclosure, the monitoring equipment / sensors of the geological disaster prevention and control system can be deployed in an open and stable location upstream of the hydropower station dam. This allows for monitoring of key monitoring areas such as the upstream side surface of the dam, the left bank dam shoulder slope, and the dam front accumulation slope.

[0046] In this embodiment, the acquisition module is used to collect data associated with the hydropower station to obtain the associated data. The acquisition module can collect data through on-site surveys; use fixed-wing UAVs for all-area low-altitude oblique photogrammetry; or coordinate with other equipment to obtain historical earthquake monitoring records of the hydropower station, retrieve hydropower station engineering design data, dam seismic fortification standards, slope support construction data, and historical data on reservoir water storage operation; deploy strong earthquake sensors and GNSS static monitoring points to collect baseline vibration data and baseline three-dimensional coordinate data under normal conditions without disaster disturbances; and deploy automated rainfall monitoring stations, groundwater level monitoring instruments, and reservoir water level monitoring terminals to collect initial environmental data such as normal rainfall, groundwater depth, and reservoir water level fluctuations, etc. This embodiment does not limit the scope of the acquisition module.

[0047] In this embodiment, the acquisition module consists of a strong earthquake monitoring instrument, a GNSS monitoring station, a vibration sensor, and a UAV payload (such as a high-resolution visible light camera or an infrared thermal imager), covering the entire hydropower station area and acquiring multi-source information such as earthquake data, terrain data, and disaster images in real time.

[0048] For example, the data acquisition module collects topographic data, geological and soil characteristics data, basic data for strong earthquake site monitoring, static benchmark deformation data, reservoir area hydrological environment data, and hydropower project disturbance construction data of the entire hydropower station area as related data for the hydropower station.

[0049] In this embodiment, the processing module is used to divide the disaster area of ​​the hydropower station based on the collected data and determine the disaster information of areas with different risk levels; and the linkage inspection module controls the drone to inspect the areas with abnormal risk levels. In this way, the early warning module can determine the comparison result based on the difference between the inspection result and the initial collected data, and then generate a prevention and control strategy for the abnormal risk level areas to effectively prevent and control the abnormal risk level areas.

[0050] To further illustrate the technical solutions provided by the embodiments of this disclosure, a detailed description is provided below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of this disclosure provide method operation steps as shown in the following embodiments or drawings, the method may include more or fewer operation steps based on conventional or non-inventive methods. In steps where there is no logically necessary causal relationship, the execution order of these steps is not limited to the execution order provided by the embodiments of this disclosure. In actual processing or when the device executes the method, it may be executed sequentially or in parallel according to the method shown in the embodiments or drawings.

[0051] The following combination Figure 3 The flowchart shown illustrates the UAV inspection method based on a strong earthquake monitoring system in this embodiment of the present disclosure. Figure 3The steps shown can be performed by electronic devices, such as... Figure 1 The service device 120 shown is performing the operation.

[0052] Step 301: Based on the associated data of the target hydropower station and the geological disaster assessment model, determine the disaster area information of the target hydropower station; the disaster area information includes the safety warning thresholds of various disaster indicators for each level of risk area within the target hydropower station.

[0053] In this embodiment of the disclosure, the associated data of the target hydropower station can be obtained first, and then the associated data of the target hydropower station can be processed by geological disaster evaluation models constructed in various ways, so as to determine the disaster area information of the target hydropower station.

[0054] In this embodiment of the disclosure, the geological hazard assessment model includes at least two mutually independent optional implementation paths, which include a first implementation path based on the geological hazard susceptibility weighted assessment rule and a second implementation path based on entropy weight-grey relational analysis.

[0055] In this disclosure, in order to better introduce the disaster area information of the target hydropower station, two specific embodiments are described below.

[0056] Example 1: In this exemplary embodiment, the following data can be collected as associated data for the target hydropower station: topographic data, geological and soil characteristic data, basic data for strong earthquake site monitoring, static benchmark deformation data, reservoir hydrological environment data, and hydropower project disturbance construction data. The topographic data includes slope gradient, slope elevation difference, topographic relief, free face height, and global digital elevation model (DEM) elevation data. The geological and soil characteristic data includes stratum lithology, rock weathering grade, rock and soil anti-sliding stability coefficient, fault fracture zone distribution, and fracture development degree. The basic data for strong earthquake site monitoring includes regional historical seismic intensity, site ground acceleration parameters, earthquake influence range, and seismic fortification benchmark values. The GNSS static benchmark deformation data includes initial values ​​of normal static horizontal displacement, initial values ​​of vertical settlement, and initial slope dip angle data. The reservoir hydrological environment data includes reservoir water level fluctuations, groundwater depth, regional rainfall, and slope soil moisture content. Construction disturbance data for hydropower projects include dam filling load, excavation slope height, slope support integrity, and the volume and distribution of waste stockpiles.

[0057] In this exemplary embodiment, the various index data of the aforementioned collected associated data can be transformed into dimensionless data to obtain a first dataset; wherein, the first dataset contains standardized index scores of the grid cells of the target hydropower station.

[0058] In this exemplary embodiment, based on the associated data and the hierarchical index list, various index data, i.e. all disaster-causing factors, can be determined, thereby classifying all disaster-causing factors by type. Then, quantitative value assignment is performed on qualitative disaster-causing factors, interval classification and calibration are performed on factors with clear safety interval thresholds, and range standardization is performed on continuously changing quantitative numerical factors. In other words, various index data are uniformly generated into dimensionless scores of 0 to 100, and finally summarized to form the first dataset.

[0059] In this exemplary embodiment, a comprehensive evaluation value of geological hazard susceptibility can be calculated on a grid-by-grid basis based on the weighted evaluation rules for geological hazard susceptibility and the first dataset to obtain a second dataset.

[0060] In an exemplary embodiment, the weighted evaluation rule for geological hazard susceptibility is determined as follows: a three-level evaluation index system is established based on associated data, and a hierarchical index list is determined based on the three-level evaluation index system; wherein, the three-level evaluation index system sets the target layer as the comprehensive evaluation of geological hazard susceptibility of hydropower stations from top to bottom, the criterion layer is divided into geological foundation conditions, strong earthquake disturbance conditions, hydrological permeability conditions, and engineering disturbance conditions, and the index layer is the subdivided disaster-causing factors under each criterion dimension; according to the index attribution relationship within the hierarchical index list, pairwise comparison judgment matrices are constructed between each index under the criterion layer to obtain multiple sets of initial judgment matrices; consistency verification is performed on multiple sets of initial judgment matrices to obtain qualified judgment matrices, and the index weight coefficients are solved based on the qualified judgment matrices to determine the weighted evaluation rule for geological hazard susceptibility based on the index weight coefficients.

[0061] In this exemplary embodiment, the second dataset and the disaster risk level division interval can be matched to determine the disaster susceptibility level of each grid cell. Then, based on the disaster susceptibility level of each grid cell, the vector boundary coordinates of each risk level area within the target hydropower station, the main disaster-causing factors, and the safety warning thresholds of various disaster indicators can be determined to identify the disaster area information of the target hydropower station.

[0062] In this exemplary embodiment, after determining the disaster susceptibility level of each grid cell, the risk category of the grid cell can be automatically determined based on the correspondence between the preset comprehensive evaluation value and the corresponding interval of the disaster risk level, according to the comprehensive evaluation value of the grid cell. This allows for the determination of the high-risk disaster area, medium-risk disaster area, low-risk hidden danger area, and safe and stable area of ​​the target hydropower station. In other words, the risk areas of the target hydropower station at each level are obtained. Furthermore, the vector boundary coordinates, main disaster-causing factors, and safety warning thresholds of these four risk areas are determined to obtain the disaster area information of the target hydropower station. In other words, the disaster area information of the target hydropower station includes four risk areas, as well as the vector boundary coordinates, main disaster-causing factors, and safety warning thresholds for each area.

[0063] In this exemplary embodiment, the evaluation levels are divided and the index weights are determined based on industry engineering experience. When dividing the disaster risk areas of hydropower stations, the risk assessment of key areas such as dam body and steep slopes in reservoir area can be strengthened in a targeted manner. The risk zoning boundaries are clear and the level division is in line with the on-site management and control needs. It can quickly distinguish between high, medium, low and safe areas. The zoning results are easy to directly match with differentiated monitoring and early warning standards and UAV inspection operation plans. The zoning is highly practical and adaptable to the site.

[0064] The geological hazard assessment model disclosed herein includes two independent parallel implementation paths, which can be selected from either one: the aforementioned embodiment one is an implementation scheme based on the weighted rules of the analytic hierarchy process (AHP), while the following embodiment two is a parallel implementation scheme based on entropy weight-grey relational analysis. Both schemes can adapt to the data foundation and accuracy requirements of different hydropower stations and can be flexibly selected according to the actual scenario; this disclosure does not impose any limitations on either approach. Specifically, the implementation scheme based on the weighted rules of the AHP is suitable for large hydropower stations with complete geological exploration data and mature engineering experience; the scheme based on entropy weight-grey relational analysis is suitable for small and medium-sized hydropower stations in canyons with large data sample sizes and frequent hidden and gradual hazard events. The system supports one-click model switching, and automatically recalculates the overall risk zoning and early warning thresholds after switching. The thresholds for the two models are stored independently.

[0065] Example 2: In this exemplary embodiment, the topographic data, geological and soil characteristics data, strong earthquake site monitoring basic data, static benchmark deformation data, reservoir area hydrological environment data, and hydropower project disturbance construction data of the target hydropower station can be collected by actual measurement and used as the associated data of the target hydropower station.

[0066] In this exemplary embodiment, the associated data can be segmented to determine positive stability indicators and negative hazard indicators. Then, the positive stability indicators and negative hazard indicators are subjected to dimensionless normalization using the range standardization method to obtain a standardized disaster-causing factor sequence with unified dimensions. Finally, based on the critical thresholds of the factors corresponding to various disasters at the target hydropower station, a critical standard reference sequence for disaster outbreak is constructed.

[0067] In this exemplary embodiment, the grey relational coefficient between the critical standard reference sequence for disaster outbreak and the standardized disaster-causing factor sequence can be calculated to construct a grey relational degree matrix of disaster hazards in the whole-domain grid unit; then, based on the grey relational degree matrix of disaster hazards and the weight coefficients of all disaster-causing factors, the grey relational result set is determined; and based on the grey relational result set and the preset mapping relationship, the disaster area information of the target hydropower station is determined; wherein, the weight coefficients of all disaster-causing factors are determined based on the entropy weight method algorithm and the standardized disaster-causing factor sequence.

[0068] In this exemplary embodiment, the preset mapping relationship is a one-to-one correspondence mapping rule between the pre-constructed weighted gray relational degree numerical interval and the disaster risk level. This mapping rule is generated by combining the historical statistical data of geological disasters in the area where the hydropower station is located, the conclusions of special on-site investigations of the project, and the general threshold requirements for geological disaster investigations of hydropower stations. After the preset mapping relationship is calibrated, it can be directly stored in the rule base of the geological disaster prevention and control system. Subsequently, the boundary thresholds of each interval can be dynamically fine-tuned according to the on-site monitoring data of the actual operation stage of the hydropower station to adapt to the differentiated geological conditions of different hydropower stations.

[0069] For example, areas with a weighted grey relational degree in the high threshold range (weighted grey relational degree ≥ 0.85) are designated as high-risk areas, prone to landslides, rock collapses, and uneven dam settlement. Areas with a weighted grey relational degree in the middle threshold range (0.6 ≤ weighted grey relational degree < 0.85) are designated as medium-risk areas, prone to localized landslides and shallow slippage under strong earthquakes and sudden water level changes. Areas with a weighted grey relational degree in the low threshold range (0.3 ≤ weighted grey relational degree < 0.6) are designated as low-risk areas, with only minor potential hazards under extreme conditions. Areas with extremely low weighted grey relational degree (weighted grey relational degree < 0.3) are designated as safe and stable areas, with no conditions for geological hazard development. Furthermore, the vector coordinates of the four-level risk areas can be entered into the geological hazard prevention and control system to complete the delineation of regional electronic fences. Furthermore, the designated areas are spatially linked to the subsequent strong earthquake monitoring system and GNSS monitoring points, clarifying the risk zone to which each monitoring point belongs. Based on the risk level of the area, safety warning thresholds are preset, including displacement warning thresholds (horizontal displacement warning value, vertical settlement warning value), strong earthquake intensity safety warning thresholds, etc., laying a data foundation for subsequent abnormality trigger inspections.

[0070] As can be seen, in this exemplary embodiment, based on measured data and combined with grey relational analysis, the degree of closeness between the actual site conditions and the critical conditions of disasters can be accurately compared. The risk areas delineated can truly reflect the actual instability tendency of mountain slopes and dam areas, accurately identify hidden and gradually changing disaster hazards, and the risk zoning results are more objective, have higher zoning precision, and are more in line with the actual disaster susceptibility distribution under the complex geological conditions of large hydropower stations.

[0071] Step 302: Obtain the real-time monitoring value of the strong earthquake monitoring system, and compare the real-time monitoring value with the safety warning threshold in the disaster area information to obtain the first comparison result.

[0072] In this embodiment, monitoring can be performed solely based on a strong earthquake monitoring system. For example, an integrated strong earthquake acceleration sensor and seismic intensity acquisition terminal, comprising the strong earthquake monitoring system, can be deployed at key locations such as the dam crest, dam abutment, top of steep slopes, and reservoir area mountains. Alternatively, monitoring can be fused between the strong earthquake monitoring system and GNSS displacement monitoring. For instance, in hydropower stations, in addition to retaining the aforementioned integrated strong earthquake acceleration sensor and seismic intensity acquisition terminal, a BeiDou GNSS high-precision displacement monitoring terminal, tilt monitor, and settlement observation sensor can be overlaid. Of course, other monitoring equipment can also be overlaid, and this embodiment does not limit this.

[0073] In an exemplary embodiment, if monitoring is performed solely based on a strong earthquake monitoring system, the strong ground motion intensity observation data within the real-time monitoring values ​​and the strong ground motion intensity safety warning threshold within the disaster area information are compared to obtain a first comparison result.

[0074] In an exemplary embodiment, if the strong earthquake monitoring system and GNSS displacement fusion monitoring are used, the first comparison result is determined based on the comparison result of the strong ground motion intensity observation data in the real-time monitoring value and the strong ground motion intensity safety warning threshold in the disaster area information, and the comparison result of the three-dimensional displacement data in the real-time monitoring value and the displacement warning threshold in the disaster area information.

[0075] Step 303: When it is determined that the first sub-comparison result in the first comparison result indicates an anomaly, control the UAV to inspect the risk area of ​​the anomaly level corresponding to the first sub-comparison result and obtain the actual inspection data.

[0076] In this embodiment of the disclosure, when it is determined that the first sub-comparison result in the first comparison result indicates an anomaly, an inspection task can be generated for the risk area of ​​the anomaly level; wherein, the parameters of the inspection task include the UAV take-off and landing coordinates, the operation inspection altitude, the image shooting angle and the aerial survey sampling density; the UAV is controlled to execute the inspection task to obtain the inspection measurement data.

[0077] To better illustrate the solution, the following example demonstrates the process of obtaining actual inspection data.

[0078] When a GNSS monitoring point in an abnormally high-risk area detects a horizontal displacement of 3.2 mm and the strong earthquake monitoring system records a peak ground acceleration of 0.35 g, both parameters are deemed to be out of limit, automatically triggering a drone inspection mission. The target area for this drone inspection mission is the 1#-3# high-risk slopes on the left bank of the hydropower station reservoir. This area is classified as an abnormally high-risk zone and is located within a forested area, with the slope surface and surrounding area covered by dense trees. Therefore, conventional optical imagery can only acquire surface vegetation information and cannot penetrate the forest to obtain accurate ground deformation data, failing to meet the accuracy requirements for slope hazard identification. Thus, a multi-rotor oblique photography drone is used for this inspection mission. In addition to carrying a positioning module, a five-lens oblique camera, and a laser obstacle avoidance sensor, it can also be equipped with an airborne LiDAR device. This airborne LiDAR device can penetrate vegetation to directly acquire high-precision point cloud data of the forest floor, with overall measurement accuracy higher than traditional optical imagery data, effectively ensuring the accuracy of high slope hazard detection in forest areas.

[0079] The parameters for the inspection mission in this high-risk area are as follows: Take-off and landing points: Select the preset main take-off and landing points in the factory area. Real-Time Kinematic (RTK) calibration will be completed before take-off to ensure positioning accuracy of ±1cm. Considering that this flight is based on the accurate basic terrain model obtained in the early stage, this inspection mission will be carried out at a fixed altitude of 35m. This altitude is within the 30-50m safe flight altitude range required for high slopes. It should be noted that when performing low-altitude flight missions in areas with high slopes and vegetation coverage, if the accuracy of the previously obtained reference DEM is insufficient, there may be a flight risk of collision with vegetation or slopes. If the aforementioned situation exists, the flight altitude can be adaptively adjusted based on the actual situation. This embodiment does not limit this. Shooting Angles: A three-view combination shooting method is used, for example: overhead angle: -30° (capturing the top of the slope and the overall deformation of the slope surface); horizontal side angle: 0° (capturing cracks and slippage marks in the middle of the slope); upward angle: +45° (capturing the lower part of the slope and the accumulation at the toe of the slope). Sampling Density: Strictly follows the standards for abnormal risk areas, for example, forward overlap rate: 85% (longitudinal overlap of continuous images in the same flight band), lateral overlap rate: 75% (lateral overlap of images in adjacent flight bands), single photo shooting interval: 1.2 seconds, video recording is enabled simultaneously (4K resolution, 30 frames / second). No-Fly Rules: Preset no-fly zone coordinates are automatically loaded, and the flight path automatically avoids the area, with a avoidance distance of no less than 50m.

[0080] The drone autonomously takes off from the main take-off and landing point, flying along a preset route to the slope area of ​​the target abnormal risk zone at a speed of 6 m / s. Upon reaching the area boundary, it automatically adjusts to an inspection height of 35 m and conducts strip aerial surveys in the order of "top → middle → bottom," with a spacing of 8 m between the flight strips. During the flight, the drone monitors the surrounding environment in real time using laser obstacle avoidance sensors, automatically detouring around any sudden obstacles (detouring radius ≥ 10 m). After completing full-area coverage photography, it returns to the main take-off and landing point along the original route, collecting 1286 high-definition images and 3 4K video clips (total duration 45 minutes), obtaining actual inspection data, and uploading the actual inspection data to the geological disaster prevention and control system, while simultaneously triggering a comparison and analysis process with the initial baseline model data within the associated data.

[0081] If ground communication is interrupted after an earthquake, the drone supports offline pre-storage of flight routes, can autonomously complete all inspection operations, and upload the inspection data offline after returning to base, thus ensuring data collection under extreme disaster conditions.

[0082] Step 304: Compare the actual inspection data with the related data to obtain the second comparison result, and generate a prevention and control strategy for the abnormal risk area based on the second comparison result.

[0083] In this embodiment of the disclosure, the measured elevation data in the inspection and measurement data and the benchmark deformation data in the associated data can be compared to obtain the terrain comparison result; wherein, the terrain comparison result is used to indicate whether the anomaly level risk area has subsidence, uplift, or soil slippage; feature recognition processing is performed on the real-scene image data in the inspection and measurement data to obtain post-disaster features; and feature recognition processing is performed on the topographic data in the associated data to obtain benchmark distribution features, and the post-disaster features and benchmark distribution features are compared to obtain the distribution comparison result; and a second comparison result is determined based on the terrain comparison result and the distribution comparison result.

[0084] In this embodiment, the anomaly level determination rule for the second comparison result is preset with a clear quantitative threshold, which is generated in combination with the industry standard for geological disaster prevention and control of hydropower stations and the statistical data of historical disasters in the project. For example, if the deformation of the terrain comparison result is in the range of greater than 0 mm and less than 3 mm, and the pixel offset of the post-disaster features in the distribution comparison result relative to the baseline distribution features is less than 5%, then the anomaly level is determined to be Level 1, corresponding to a low degree of local deformation hazard with no overall instability risk; if the deformation of the terrain comparison result is in the range of greater than 3 mm and less than 10 mm, and the pixel offset of the post-disaster features in the distribution comparison result relative to the baseline distribution features is in the range of 5% to 20%, then the anomaly level is determined to be Level 2, corresponding to a moderate local slippage hazard with a risk of local collapse; if the deformation of the terrain comparison result is greater than 10 mm, and the pixel offset of the post-disaster features in the distribution comparison result relative to the baseline distribution features exceeds 20%, then the anomaly level is determined to be Level 3, corresponding to a severe overall instability hazard with a high probability of landslides and rock collapses.

[0085] In this embodiment of the disclosure, the threshold boundaries of different levels can be dynamically adapted and adjusted according to the actual engineering parameters of the target hydropower station's dam body level and slope soil and rock characteristics. Once determined, they can be directly stored in the system rule base without needing to be reconfigured each time.

[0086] In this embodiment of the disclosure, a graded prevention and control strategy is generated based on the anomaly level indicated by the second comparison result. For example, when the anomaly level indicated by the second comparison result is level one, a level one prevention and control strategy is generated, which includes triggering an audible and visual alarm and pushing early warning information to the on-site operation and maintenance terminal; when the anomaly level indicated by the second comparison result is level two, a level two prevention and control strategy is generated, which includes, based on the level one prevention and control strategy, simultaneously initiating fixed-point re-patrols by drones and increasing the monitoring frequency; when the anomaly level indicated by the second comparison result is level three, a level three prevention and control strategy is generated, which includes, based on the level two prevention and control strategy, automatically triggering an emergency response plan and notifying the superior dispatch center.

[0087] In this embodiment of the disclosure, the output forms of the above-mentioned prevention and control strategies at each level may include digital data reports, visual graphic reports, and real-scene audio-visual evidence reports, etc. The aforementioned reports are directly pushed to the management and control screen of the geological disaster prevention and control system, and simplified versions of hazard briefings, locations of dangerous points, and on-site real-scene pictures are pushed to front-line maintenance personnel and reservoir area patrol personnel through dedicated operation and maintenance applications, WeChat government affairs terminals, message notification groups, SMS, etc., so as to achieve rapid information transmission and improve the timeliness and comprehensiveness of disaster prevention and control.

[0088] Exemplary embodiments of this disclosure also provide a drone inspection device based on a strong earthquake monitoring system. (See reference...) Figure 4 As shown, the UAV inspection device 400 based on the strong earthquake monitoring system includes the following program units: The first processing unit 401 is used to determine the disaster area information of the target hydropower station based on the associated data and geological disaster assessment model of the target hydropower station; the disaster area information includes the safety warning thresholds of various disaster indicators for each level of risk area within the target hydropower station; The comparison unit 402 is used to obtain the real-time monitoring value of the strong earthquake monitoring system and compare the real-time monitoring value with the safety warning threshold in the disaster area information to obtain the first comparison result; The inspection unit 403 is used to control the drone to inspect the risk area of ​​the abnormal level corresponding to the first sub-comparison result when it is determined that the first sub-comparison result in the first comparison result indicates an abnormality, and to obtain the actual inspection data. The second processing unit 404 is used to compare the actual inspection data with the associated data to obtain a second comparison result, and generate a prevention and control strategy for the abnormal level risk area based on the second comparison result.

[0089] In one possible implementation, the first processing unit 401 is configured to: Collect topographic and geomorphological data, geological and soil characteristics data, strong earthquake site monitoring basic data, static benchmark deformation data, reservoir area hydrological environment data, and hydropower project disturbance construction data of the target hydropower station as associated data for the target hydropower station; The various indicator data of the associated data are transformed into dimensionless data to obtain a first dataset; wherein, the first dataset contains standardized indicator scores of the grid cells of the target hydropower station; Based on the weighted evaluation rules for geological hazard susceptibility and the first dataset, the comprehensive evaluation value of geological hazard susceptibility is calculated for each grid cell to obtain the second dataset; The second dataset and the disaster risk level division intervals are matched to determine the disaster susceptibility level of each grid cell; Based on the disaster susceptibility level of each grid cell, the vector boundary coordinates, main disaster-causing factors, and safety warning thresholds of various disaster indicators of each level of risk area within the target hydropower station are determined to identify the disaster area information of the target hydropower station.

[0090] In one possible implementation, the weighted evaluation rule for geological hazard susceptibility is determined based on the following method: Based on the aforementioned associated data, a three-level evaluation index system is established, and based on the three-level evaluation index system, a hierarchical index list is determined; wherein, the three-level evaluation index system sets the target layer as the comprehensive evaluation of the geological hazard susceptibility of hydropower stations from top to bottom, the criterion layer is divided into geological basic conditions, strong earthquake disturbance conditions, hydrological permeability conditions and engineering disturbance conditions, and the index layer is the subdivided disaster-causing factors under each criterion dimension. Based on the hierarchical index list, construct pairwise comparison judgment matrices between each index under the criterion layer to obtain multiple sets of initial judgment matrices. Consistency verification is performed on the multiple sets of initial judgment matrices to obtain qualified judgment matrices, and the index weight coefficients are solved based on the qualified judgment matrices to determine the weighted evaluation rules for geological hazard susceptibility.

[0091] In one possible implementation, the first processing unit 401 is configured to: Collect topographic and geomorphological data, geological and soil characteristics data, strong earthquake site monitoring basic data, static benchmark deformation data, reservoir area hydrological environment data, and hydropower project disturbance construction data of the target hydropower station as associated data for the target hydropower station; The associated data is divided to determine positive stable indicators and negative hazard indicators. The positive stable indicators and negative hazard indicators are then normalized using the range standardization method to obtain a standardized disaster-causing factor sequence with unified dimensions. Based on the critical thresholds of various disasters corresponding to the target hydropower station, a critical standard reference sequence for disaster outbreak is established; Calculate the grey relational coefficient between the critical standard reference sequence for disaster outbreak and the standardized disaster-causing factor sequence, and construct a grey relational degree matrix of disaster risks for the entire grid unit. Based on the gray relational degree matrix of the disaster hazard and the weight coefficients of all disaster-causing factors, a gray relational degree result set is determined; and based on the gray relational degree result set and the preset mapping relationship, the disaster area information of the target hydropower station is determined; wherein, the weight coefficients of all disaster-causing factors are determined based on the entropy weight algorithm and the standardized disaster-causing factor sequence.

[0092] In one possible implementation, the comparison unit 402 is used for: The strong ground motion intensity observation data within the real-time monitoring values ​​are compared with the strong ground motion intensity safety warning threshold within the disaster area information to obtain a first comparison result; or, Based on the comparison results of the strong ground motion intensity observation data within the real-time monitoring values ​​and the strong ground motion intensity safety warning threshold within the disaster area information, and the comparison results of the three-dimensional displacement data within the real-time monitoring values ​​and the displacement warning threshold within the disaster area information, a first comparison result is determined.

[0093] In one possible implementation, the inspection unit 403 is used for: Generate inspection tasks for the aforementioned abnormal risk areas; wherein the parameters of the inspection tasks include the UAV take-off and landing coordinates, the operation and inspection altitude, the image shooting angle, and the aerial survey sampling density; Control the drone to perform the inspection task and obtain the actual inspection data.

[0094] In one possible implementation, the second processing unit 404 is configured to: The measured elevation data in the inspection data and the benchmark deformation data in the associated data are compared to obtain the terrain comparison result; wherein, the terrain comparison result is used to indicate whether the anomaly level risk area has subsidence, uplift, or soil slippage. The real-scene image data within the inspection and measurement data is processed for feature recognition to obtain post-disaster features; and the topographic data within the associated data is processed for feature recognition to obtain baseline distribution features, and the post-disaster features and the baseline distribution features are compared to obtain distribution comparison results. Based on the terrain comparison results and distribution comparison results, a second comparison result is determined.

[0095] Each program unit on the device side in this disclosure is mapped to a corresponding program unit. Figure 2 The geological disaster prevention and control system has four main functional modules, among which the first processing unit corresponds to Figure 2 The processing module and the comparison unit span both the acquisition module and the processing module. The data acquisition stage corresponds to the acquisition module, the threshold comparison calculation stage corresponds to the processing module, and the inspection unit corresponds to... Figure 2 The inspection module in the middle, the second processing unit corresponds to Figure 2 The early warning module in the system.

[0096] The specific details of each part of the above-mentioned device have been described in detail in the method section of the implementation plan. For any undisclosed details, please refer to the implementation plan of the method section, and therefore will not be repeated here.

[0097] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to exemplary embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0098] An exemplary embodiment of this disclosure also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the aforementioned unmanned aerial vehicle (UAV) inspection method based on a strong earthquake monitoring system.

[0099] In one implementation, the computer program product can be a tangible product containing a computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium can be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory, hard disk drive (HDD), solid-state drive (SSD), etc. For example, the computer program product can be implemented as a non-volatile storage medium storing a computer program, such as read-only memory, NAND flash memory, etc.

[0100] In one implementation, the computer program product can be an intangible product containing a computer program. For example, the computer program product can be implemented as a virtual digital product, such as an executable file, installation package, or other digital file storing the computer program.

[0101] Computer program code can be written in one or more programming languages. Examples of programming languages ​​include C, Java, and C++. Program code can execute entirely on the user's computing device, partially on the user's computing device, or as a standalone software package. It can also execute partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, such as a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via an internet connection provided by a mobile network operator).

[0102] Computer programs can be carried or transmitted via signals such as electricity, magnetism, light, electromagnetic waves, and infrared radiation. Electronic devices can convert the signals carrying computer programs into digital signals, thereby enabling the computer programs to run. When a computer program runs on an electronic device, its code is used to cause the electronic device to execute (more specifically, the processor of the electronic device to execute) the method steps of various exemplary embodiments of this disclosure, such as the above-described UAV inspection method based on a strong earthquake monitoring system, which includes the following steps: Step 301: Determine the disaster area information of the target hydropower station based on the associated data and geological disaster evaluation model; the disaster area information includes the safety warning thresholds of various disaster indicators for each level of risk area within the target hydropower station; Step 302: Obtain the real-time monitoring value of the strong earthquake monitoring system, and compare the real-time monitoring value with the safety warning thresholds within the disaster area information to obtain a first comparison result; Step 303: When it is determined that the first sub-comparison result in the first comparison result indicates an anomaly, control the UAV to inspect the abnormal level risk area corresponding to the first sub-comparison result to obtain the inspection measurement data; Step 304: Compare the inspection measurement data with the associated data to obtain a second comparison result, and generate a prevention and control strategy for the abnormal level risk area based on the second comparison result.

[0103] By implementing the above methods and steps through computer programs, the disaster area information of the target hydropower station can be determined based on the associated data and geological disaster assessment model. The disaster area information includes the safety warning thresholds of various disaster indicators for each risk level within the target hydropower station. In other words, this disclosure builds a geological disaster assessment model based on multi-source initial basic data of the target hydropower station, which can accurately classify disaster-prone areas across the entire region and clearly define the high, medium, and low risk control areas in advance. Compared with the traditional aimless blind inspection mode, this allows subsequent drone inspection operations to accurately focus on high-risk areas, improving the targeting and efficiency of inspection operations from the source, and realizing the transformation of geological disasters from post-disaster handling to pre-disaster prediction and control.

[0104] In this embodiment of the disclosure, real-time monitoring values ​​of a strong earthquake monitoring system can be obtained, and the real-time monitoring values ​​can be compared with safety warning thresholds within disaster area information to obtain a first comparison result; when it is determined that the first sub-comparison result in the first comparison result indicates an anomaly, the drone is controlled to inspect the anomaly-level risk area corresponding to the first sub-comparison result to obtain inspection measurement data; and the inspection measurement data is compared with associated data to obtain a second comparison result, and a prevention and control strategy for the anomaly-level risk area is generated based on the second comparison result.

[0105] As can be seen, this invention integrates a strong earthquake monitoring system to collect core data such as seismic intensity in the affected area, automatically comparing the data with preset safety warning thresholds without manual intervention. In the event of abnormal conditions such as earthquake disturbances, slope slippage, or dam deformation, it can quickly determine the anomaly and automatically control drones for inspection, eliminating the lag in manual detection and significantly shortening the response time for on-site investigations after a disaster. Furthermore, the automatic drone inspection after a hazard is triggered eliminates the need for personnel to enter high-risk disaster sites such as landslides and rockfalls for on-site investigations, completely avoiding personal safety hazards caused by rockfalls and secondary landslides in mountainous disaster areas. It also overcomes the limitations of manual inspections due to terrain, weather, and nighttime conditions, expanding the operational scenarios for data collection at disaster sites. Furthermore, the rapid analysis of real-time inspection data and related data obtained by drones after the earthquake allows for the precise identification of potential hazards around the disaster site, prediction of secondary geological disaster risks such as landslides and bank collapses induced by aftershocks, and generation of prevention and control strategies that are easy for operation and maintenance management units to manage. This comprehensively strengthens the overall disaster prevention, mitigation, and safe operation guarantee capabilities of the target hydropower station reservoir area and dam area, thereby improving the disaster prevention and control effect of the hydropower station.

[0106] Exemplary embodiments of this disclosure also provide an electronic device, which may include a processor and a memory. The memory stores executable instructions for the processor, such as computer programs. The processor executes the executable instructions to perform the method steps of various exemplary embodiments of this disclosure.

[0107] The following is for reference. Figure 5 The electronic device is illustrated by way of a general-purpose computing device. It should be understood that... Figure 5 The electronic device 500 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0108] like Figure 5 As shown, the electronic device 500 may include: a processor 510, a memory 520, a bus 530, an I / O (input / output) interface 540, and a network adapter 550.

[0109] The memory 520 may include volatile memory, such as RAM 521 and cache unit 522, and may also include non-volatile memory, such as ROM 523. The memory 520 may also include one or more program modules 524, including but not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. For example, program module 524 may include the units described in the above-described apparatus.

[0110] The processor 510 may include one or more processing units, such as an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor, and / or an NPU (Neural-Network Processing Unit).

[0111] The processor 510 can be used to execute executable instructions stored in the memory 520, such as the above-mentioned UAV inspection method based on a strong earthquake monitoring system, which includes the following steps: Step 301: Determine the disaster area information of the target hydropower station based on the associated data and geological disaster evaluation model; the disaster area information includes the safety warning thresholds of various disaster indicators for each level of risk area within the target hydropower station; Step 302: Obtain the real-time monitoring value of the strong earthquake monitoring system, and compare the real-time monitoring value with the safety warning thresholds within the disaster area information to obtain a first comparison result; Step 303: When it is determined that the first sub-comparison result in the first comparison result indicates an anomaly, control the UAV to inspect the abnormal level risk area corresponding to the first sub-comparison result and obtain the inspection measurement data; Step 304: Compare the inspection measurement data with the associated data to obtain a second comparison result, and generate a prevention and control strategy for the abnormal level risk area based on the second comparison result.

[0112] By executing the above method steps through processor 510, the disaster area information of the target hydropower station can be determined based on the associated data and geological disaster assessment model. The disaster area information includes the safety warning thresholds of various disaster indicators for each level of risk area within the target hydropower station. In other words, this disclosure builds a geological disaster assessment model based on multi-source initial basic data of the target hydropower station, which can accurately classify disaster-prone areas across the entire region and clearly define the high, medium, and low risk control areas in advance. Compared with the traditional aimless blind inspection mode, this allows subsequent drone inspection operations to accurately focus on areas with high incidence of hidden dangers, improving the targeting and efficiency of inspection operations from the source, and realizing the transformation of geological disasters from post-event handling to pre-event prediction and control.

[0113] In this embodiment of the disclosure, real-time monitoring values ​​of a strong earthquake monitoring system can be obtained, and the real-time monitoring values ​​can be compared with safety warning thresholds within disaster area information to obtain a first comparison result; when it is determined that the first sub-comparison result in the first comparison result indicates an anomaly, the drone is controlled to inspect the anomaly-level risk area corresponding to the first sub-comparison result to obtain inspection measurement data; and the inspection measurement data is compared with associated data to obtain a second comparison result, and a prevention and control strategy for the anomaly-level risk area is generated based on the second comparison result.

[0114] As can be seen, this invention integrates a strong earthquake monitoring system to collect core data such as seismic intensity in the affected area, automatically comparing the data with preset safety warning thresholds without manual intervention. In the event of abnormal conditions such as earthquake disturbances, slope slippage, or dam deformation, it can quickly determine the anomaly and automatically control drones for inspection, eliminating the lag in manual detection and significantly shortening the response time for on-site investigations after a disaster. Furthermore, the automatic drone inspection after a hazard is triggered eliminates the need for personnel to enter high-risk disaster sites such as landslides and rockfalls for on-site investigations, completely avoiding personal safety hazards caused by rockfalls and secondary landslides in mountainous disaster areas. It also overcomes the limitations of manual inspections due to terrain, weather, and nighttime conditions, expanding the operational scenarios for data collection at disaster sites. Furthermore, the rapid analysis of real-time inspection data and related data obtained by drones after the earthquake allows for the precise identification of potential hazards around the disaster site, prediction of secondary geological disaster risks such as landslides and bank collapses induced by aftershocks, and generation of prevention and control strategies that are easy for operation and maintenance management units to manage. This comprehensively strengthens the overall disaster prevention, mitigation, and safe operation guarantee capabilities of the target hydropower station reservoir area and dam area, thereby improving the disaster prevention and control effect of the hydropower station.

[0115] Bus 530 is used to connect different components of electronic device 500 and may include a data bus, an address bus and a control bus.

[0116] Electronic device 500 can communicate with one or more external devices 600 (such as keyboard, mouse, external controller, etc.) through I / O interface 540.

[0117] Electronic device 500 can communicate with one or more networks via network adapter 550. For example, network adapter 550 can provide mobile communication solutions such as 3G / 4G / 5G, or wireless communication solutions such as wireless LAN, Bluetooth, and near-field communication. Network adapter 550 can communicate with other modules of electronic device 500 via bus 530.

[0118] although Figure 5As not shown in the diagram, other hardware and / or software modules may also be configured in the electronic device 500, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0119] As can be seen from the above, the technical solutions disclosed herein can be implemented as methods, apparatus, systems, computer program products, storage media, electronic devices, etc. Those skilled in the art will understand that various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which may be referred to as "circuit," "module," or "system," respectively.

[0120] It should be understood that this disclosure is not limited to the specific methods, steps, or structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. Those skilled in the art will readily conceive of other embodiments based on the specific implementations provided in this disclosure. Therefore, the specific implementations provided in this disclosure are merely exemplary, and the scope and spirit of this disclosure are indicated by the claims, and should cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary technical means in the art not disclosed in this disclosure.

Claims

1. A method for unmanned aerial vehicle (UAV) inspection based on a strong earthquake monitoring system, characterized in that, The method includes: Based on the associated data of the target hydropower station and the geological disaster assessment model, the disaster area information of the target hydropower station is determined; the disaster area information includes the safety warning thresholds of various disaster indicators for each level of risk area within the target hydropower station; The real-time monitoring values ​​of the strong earthquake monitoring system are obtained, and the real-time monitoring values ​​are compared with the safety warning thresholds in the disaster area information to obtain a first comparison result; When it is determined that the first sub-comparison result in the first comparison result indicates an anomaly, the drone is controlled to inspect the risk area corresponding to the anomaly level of the first sub-comparison result and obtain the actual inspection data. The actual inspection data is compared with the associated data to obtain a second comparison result, and a prevention and control strategy for the abnormal risk area is generated based on the second comparison result.

2. The method according to claim 1, characterized in that, Based on the associated data of the target hydropower station and the geological hazard assessment model, the hazard area information of the target hydropower station is determined, including: Collect topographic and geomorphological data, geological and soil characteristics data, strong earthquake site monitoring basic data, static benchmark deformation data, reservoir area hydrological environment data, and hydropower project disturbance construction data of the target hydropower station as associated data for the target hydropower station; The various indicator data of the associated data are transformed into dimensionless data to obtain a first dataset; wherein, the first dataset contains standardized indicator scores of the grid cells of the target hydropower station; Based on the weighted evaluation rules for geological hazard susceptibility and the first dataset, the comprehensive evaluation value of geological hazard susceptibility is calculated for each grid cell to obtain the second dataset; The second dataset and the disaster risk level division intervals are matched to determine the disaster susceptibility level of each grid cell; Based on the disaster susceptibility level of each grid cell, the vector boundary coordinates, main disaster-causing factors, and safety warning thresholds of various disaster indicators of each level of risk area within the target hydropower station are determined to identify the disaster area information of the target hydropower station.

3. The method according to claim 2, characterized in that, The weighted evaluation rules for geological hazard susceptibility are determined based on the following methods: Based on the aforementioned associated data, a three-level evaluation index system is established, and based on the three-level evaluation index system, a hierarchical index list is determined; wherein, the three-level evaluation index system sets the target layer as the comprehensive evaluation of the geological hazard susceptibility of hydropower stations from top to bottom, the criterion layer is divided into geological basic conditions, strong earthquake disturbance conditions, hydrological permeability conditions and engineering disturbance conditions, and the index layer is the subdivided disaster-causing factors under each criterion dimension. Based on the hierarchical index list, construct pairwise comparison judgment matrices between each index under the criterion layer to obtain multiple sets of initial judgment matrices. Consistency verification is performed on the multiple sets of initial judgment matrices to obtain qualified judgment matrices, and the index weight coefficients are solved based on the qualified judgment matrices to determine the weighted evaluation rules for geological hazard susceptibility.

4. The method according to claim 1, characterized in that, Based on the associated data of the target hydropower station and the geological hazard assessment model, the hazard area information of the target hydropower station is determined, including: Collect topographic and geomorphological data, geological and soil characteristics data, strong earthquake site monitoring basic data, static benchmark deformation data, reservoir area hydrological environment data, and hydropower project disturbance construction data of the target hydropower station as associated data for the target hydropower station; The associated data is divided to determine positive stable indicators and negative hazard indicators. The positive stable indicators and negative hazard indicators are then normalized using the range standardization method to obtain a standardized disaster-causing factor sequence with unified dimensions. Based on the critical thresholds of various disasters corresponding to the target hydropower station, a critical standard reference sequence for disaster outbreak is established; Calculate the grey relational coefficient between the critical standard reference sequence for disaster outbreak and the standardized disaster-causing factor sequence, and construct a grey relational degree matrix of disaster risks for the entire grid unit. Based on the gray relational degree matrix of the disaster hazard and the weight coefficients of all disaster-causing factors, a gray relational degree result set is determined; and based on the gray relational degree result set and the preset mapping relationship, the disaster area information of the target hydropower station is determined; wherein, the weight coefficients of all disaster-causing factors are determined based on the entropy weight algorithm and the standardized disaster-causing factor sequence.

5. The method according to any one of claims 1-4, characterized in that, The real-time monitoring value is compared with the safety warning threshold within the disaster area information to obtain a first comparison result, including: The strong ground motion intensity observation data within the real-time monitoring values ​​are compared with the strong ground motion intensity safety warning threshold within the disaster area information to obtain a first comparison result; or, Based on the comparison results of the strong ground motion intensity observation data within the real-time monitoring values ​​and the strong ground motion intensity safety warning threshold within the disaster area information, and the comparison results of the three-dimensional displacement data within the real-time monitoring values ​​and the displacement warning threshold within the disaster area information, a first comparison result is determined.

6. The method according to claim 5, characterized in that, When it is determined that the first sub-comparison result in the first comparison result indicates an anomaly, the drone is controlled to inspect the risk area corresponding to the anomaly level of the first sub-comparison result, and the inspection measurement data is obtained, including: Generate inspection tasks for the aforementioned abnormal risk areas; wherein the parameters of the inspection tasks include the UAV take-off and landing coordinates, the operation and inspection altitude, the image shooting angle, and the aerial survey sampling density; Control the drone to perform the inspection task and obtain the actual inspection data.

7. The method according to claim 5, characterized in that, The actual inspection data is compared with the associated data to obtain a second comparison result, including: The measured elevation data in the inspection data and the benchmark deformation data in the associated data are compared to obtain the terrain comparison result; wherein, the terrain comparison result is used to indicate whether the anomaly level risk area has subsidence, uplift, or soil slippage. The real-scene image data within the inspection and measurement data is processed for feature recognition to obtain post-disaster features; and the topographic data within the associated data is processed for feature recognition to obtain baseline distribution features, and the post-disaster features and the baseline distribution features are compared to obtain distribution comparison results. Based on the terrain comparison results and distribution comparison results, a second comparison result is determined.

8. A drone inspection device based on a strong earthquake monitoring system, characterized in that, The device includes: The first processing unit is used to determine the disaster area information of the target hydropower station based on the associated data and geological disaster assessment model; the disaster area information includes the safety warning thresholds of various disaster indicators for each level of risk area within the target hydropower station; The comparison unit is used to obtain the real-time monitoring value of the strong earthquake monitoring system and compare the real-time monitoring value with the safety warning threshold in the disaster area information to obtain the first comparison result; The inspection unit is used to control the drone to inspect the risk area corresponding to the abnormal level of the first sub-comparison result when it is determined that the first sub-comparison result in the first comparison result indicates an abnormality, and to obtain the actual inspection data. The second processing unit is used to compare the actual inspection data with the associated data to obtain a second comparison result, and generate a prevention and control strategy for the abnormal level risk area based on the second comparison result.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1 to 7.

10. An electronic device, characterized in that, include: processor; Memory for storing the executable instructions of the processor; The processor is configured to execute the method of any one of claims 1 to 7 by executing the executable instructions.

Images