Hydropower station unmanned aerial vehicle intelligent inspection method and related device

Abstract

The invention discloses a hydropower station unmanned aerial vehicle intelligent inspection method, a hydropower station unmanned aerial vehicle intelligent inspection system, a hydropower station unmanned aerial vehicle intelligent inspection device and a computer readable storage medium, and the method comprises the steps: carrying out the inspection task planning based on a hydropower station three-dimensional digital map model and inspection object characteristic data, and obtaining the inspection task data; unmanned aerial vehicle autonomous inspection data acquisition is carried out based on the inspection task data and unmanned aerial vehicle multi-dimensional data acquisition equipment to obtain inspection data; performing intelligent identification analysis on the inspection data based on a hydropower station multi-algorithm identification model to obtain a risk assessment report; wherein the hydropower station multi-algorithm identification model comprises a personnel identification algorithm, a water area identification algorithm and an equipment defect identification algorithm; performing early warning based on the risk assessment report; and filing the risk assessment report. The system adapts to the complex environment of the hydropower station, integrates multiple monitoring means, achieves the intelligent analysis and early warning inspection system, and improves the safety management level and operation reliability of the hydropower station.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of hydroelectric equipment, and more particularly relates to a hydroelectric station unmanned aerial vehicle intelligent inspection method, a hydroelectric station unmanned aerial vehicle intelligent inspection system, a hydroelectric station unmanned aerial vehicle intelligent inspection device and a computer readable storage medium. BACKGROUND

[0002] As indispensable energy infrastructure, hydroelectric stations not only bear the core responsibility of ensuring stable regional power supply, but also play an irreplaceable role in flood control and dispatching, rational utilization of water resources and other fields, and their safe and stable operation is of great significance.

[0003] In related technologies, the equipment inspection and environmental monitoring of hydroelectric stations mainly rely on traditional manual inspection methods. Manual inspection often requires inspection personnel to check point by point according to fixed routes. For large hydroelectric stations, the equipment and facilities involved, such as generator sets, water turbines, gates, transmission lines and dam structures, are widely distributed and have a large number. A single inspection often requires a large amount of time and labor cost, which is difficult to meet the needs of high-frequency and normalized inspection, resulting in potential equipment problems that are difficult to discover in time. Moreover, manual inspection has obvious limitations. Some complex terrain and harsh environment areas, such as deep dam body, underwater hidden engineering and remote transmission line sections, are difficult for manual inspection to reach or conduct detailed inspection, forming inspection blind areas, which are often high-risk areas of equipment failure and safety accidents.

[0004] Therefore, how to realize a set of inspection system that can adapt to the complex environment of hydroelectric stations, integrate multiple monitoring methods, realize intelligent analysis and early warning, and improve the safety management level and operation reliability of hydroelectric stations is an important issue for those skilled in the art. SUMMARY

[0005] The purpose of the present application is to provide a hydroelectric station unmanned aerial vehicle intelligent inspection method, a hydroelectric station unmanned aerial vehicle intelligent inspection system, a hydroelectric station unmanned aerial vehicle intelligent inspection device and a computer readable storage medium, so as to adapt to the complex environment of hydroelectric stations, integrate multiple monitoring methods, realize intelligent analysis and early warning, and improve the safety management level and operation reliability of hydroelectric stations.

[0006] In view of the above defects or improvement needs of the prior art, the present application provides a hydroelectric station unmanned aerial vehicle intelligent inspection method, comprising: planning a inspection task based on a three-dimensional digital map model of the hydroelectric station and object characteristic data of the inspection task, to obtain inspection task data; collecting unmanned aerial vehicle autonomous inspection data based on the inspection task data and a multi-dimensional data collection device of the unmanned aerial vehicle, to obtain inspection data; Intelligently identifying and analyzing the inspection data based on a hydropower station multi-algorithm identification model to obtain a risk assessment report; wherein the hydropower station multi-algorithm identification model comprises: a personnel identification algorithm, a water area identification algorithm, and a device defect identification algorithm. Based on the risk assessment report, a warning is given. The risk assessment report is archived.

[0007] Optionally, based on a hydropower station three-dimensional digital map model and inspection object characteristic data, a task planning is performed to obtain inspection task data, comprising: Based on hydropower station geographic information data, high-precision coordinate data, and labeled inspection key areas, a map model is constructed to obtain the hydropower station three-dimensional digital map model; Based on the hydropower station three-dimensional digital map model and environmental characteristic data of each inspection object, an inspection parameter device is performed to obtain corresponding inspection parameters; wherein the inspection objects comprise: river inspection, mountain slope inspection, photovoltaic component inspection, and substation equipment inspection. Based on the hydropower station three-dimensional digital map model and the inspection parameters, a path planning is performed to obtain the inspection task data.

[0008] Optionally, based on the inspection task data and a multi-dimensional data acquisition device of a drone, a drone autonomous inspection data collection is performed to obtain inspection data, comprising: Based on the inspection task data, the drone is operated to perform autonomous cruising; Multi-dimensional data acquisition is performed by the multi-dimensional data acquisition device of the drone to obtain the inspection data.

[0009] Optionally, based on the hydropower station multi-algorithm identification model, the inspection data is intelligently identified and analyzed to obtain a risk assessment report, comprising: Through the personnel identification algorithm, personnel in a dangerous area in the inspection data are identified to obtain personnel abnormal features; Through the water area identification algorithm, water area abnormalities in the inspection data are identified to obtain water area abnormal features; Through the device defect identification algorithm, device defects in the inspection data are identified to obtain device abnormal features; Based on the personnel abnormal features, the water area abnormal features, and the device abnormal features, a risk assessment report is generated.

[0010] The application also provides a hydropower station unmanned aerial vehicle intelligent inspection system, comprising: A task planning module is configured to perform a task planning based on a hydropower station three-dimensional digital map model and inspection object characteristic data to obtain inspection task data. The unmanned aerial vehicle inspection module is configured to perform unmanned aerial vehicle autonomous inspection data collection based on the inspection task data and the unmanned aerial vehicle multi-dimensional data collection device, and obtain inspection data. The inspection analysis module is configured to perform intelligent identification analysis on the inspection data based on a hydropower station multi-algorithm identification model, and obtain a risk assessment report. The hydropower station multi-algorithm identification model includes a personnel identification algorithm, a water area identification algorithm, and a device defect identification algorithm. The inspection early warning module is configured to perform early warning based on the risk assessment report. The data archiving module is configured to archive the risk assessment report.

[0011] Optionally, the task planning module is configured to perform map model construction based on hydropower station geographic information data, high-precision coordinate data, and labeled inspection key areas, and obtain a hydropower station three-dimensional digital map model. The inspection parameters are obtained based on the hydropower station three-dimensional digital map model and environmental characteristic data of each inspection object. The inspection objects include river inspection, mountain slope inspection, photovoltaic component inspection, and substation equipment inspection. The inspection task data is obtained based on the hydropower station three-dimensional digital map model and the inspection parameters.

[0012] Optionally, the unmanned aerial vehicle inspection module is configured to operate the unmanned aerial vehicle to perform autonomous cruising based on the inspection task data. The multi-dimensional data collection device is used to perform multi-dimensional data collection, and the inspection data is obtained.

[0013] Optionally, the inspection analysis module is configured to identify personnel in a dangerous area in the inspection data based on the personnel identification algorithm, and obtain personnel abnormal features. The water area abnormality in the inspection data is identified based on the water area identification algorithm, and water area abnormal features are obtained. The device defects in the inspection data are identified based on the device defect identification algorithm, and device abnormal features are obtained. The risk assessment report is generated based on the personnel abnormal features, the water area abnormal features, and the device abnormal features.

[0014] The application also provides a hydropower station unmanned aerial vehicle intelligent inspection device, which includes: A memory is configured to store a computer program. A processor is configured to execute the computer program to implement the steps of the hydropower station unmanned aerial vehicle intelligent inspection method.

[0015] The application also provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps of the hydropower station unmanned aerial vehicle intelligent inspection method.

[0016] The water power station unmanned aerial vehicle intelligent inspection method provided in the application comprises: performing inspection task planning based on a water power station three-dimensional digital map model and inspection object characteristic data to obtain inspection task data; performing unmanned aerial vehicle autonomous inspection data collection based on the inspection task data and a unmanned aerial vehicle multi-dimensional data collection device to obtain inspection data; performing intelligent identification analysis on the inspection data based on a water power station multi-algorithm identification model to obtain a risk assessment report; wherein the water power station multi-algorithm identification model comprises: a personnel identification algorithm, a water area identification algorithm, and a device defect identification algorithm; performing early warning based on the risk assessment report; and archiving the risk assessment report.

[0017] The application has the following beneficial effects: By constructing an intelligent inspection system based on a water power station three-dimensional digital map model, precise monitoring and efficient management of the entire risk of the water power station are realized. Through scientific planning of the inspection task, the flight path is optimized, and the inspection efficiency and coverage range are significantly improved. The collaborative work of the unmanned aerial vehicle multi-dimensional data collection device realizes the fusion collection of multi-modal information such as visible light, infrared, and laser, greatly improving the accuracy and comprehensiveness of abnormal detection. The parallel processing mechanism of the water power station multi-algorithm identification model enables precise identification of multiple risks such as personnel intrusion, water level abnormalities, and device defects, effectively avoiding the missed detection of safety hazards. The hierarchical early warning mechanism ensures the timely transmission of risk information, significantly shortens the emergency response time, and improves the timeliness of risk disposal. Through the systematic archiving of the risk assessment report, a complete risk knowledge base is formed, providing reliable data support for trend analysis and preventive maintenance, thereby greatly improving the overall safety management level of the water power station and effectively ensuring the safe and stable operation of the water power station. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the provided drawings.

[0019] Figure 1 A flowchart of a water power station unmanned aerial vehicle intelligent inspection method provided by the embodiments of the present application; Figure 2 A structural schematic diagram of a water power station unmanned aerial vehicle intelligent inspection system provided by the embodiments of the present application; Figure 3 A structural schematic diagram of a water power station unmanned aerial vehicle intelligent inspection device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0020] The application aims to provide a hydroelectric station unmanned aerial vehicle intelligent inspection method, a hydroelectric station unmanned aerial vehicle intelligent inspection system, a hydroelectric station unmanned aerial vehicle intelligent inspection device and a computer readable storage medium, so as to adapt to the complex environment of a hydroelectric station, integrate various monitoring means, realize intelligent analysis and early warning of the inspection system, and improve the safety management level and operation reliability of the hydroelectric station.

[0021] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application. In addition, the technical features involved in the various embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0022] The hydroelectric station unmanned aerial vehicle intelligent inspection method provided by the present application will be described below through an embodiment.

[0023] Reference is made to Figure 1 , Figure 1 The flowchart of the hydroelectric station unmanned aerial vehicle intelligent inspection method provided by the present embodiment is shown in the figure.

[0024] In the present embodiment, the method can include: S101, planning an inspection task based on a three-dimensional digital map model of a hydroelectric station and object characteristic data of an inspection object, to obtain inspection task data; The present step aims to plan an inspection task based on a three-dimensional digital map model of a hydroelectric station and object characteristic data of an inspection object, to obtain inspection task data. It is mainly considered that the terrain of a hydroelectric station is complex, the facilities are widely distributed, and different inspection objects have differentiated monitoring requirements. By constructing a high-precision three-dimensional digital map model, the spatial layout and terrain features of the hydroelectric station can be accurately mastered, and combined with the characteristic data of various inspection objects, a targeted inspection strategy can be scientifically formulated to ensure comprehensive inspection coverage, optimized path and reasonable parameters.

[0025] Optionally, the present step can include: Step 1, constructing a map model based on geographic information data of a hydroelectric station, high-precision coordinate data and marked key inspection areas, to obtain a three-dimensional digital map model of the hydroelectric station; Step 2, planning an inspection parameter based on the three-dimensional digital map model of the hydroelectric station and environmental characteristic data of each inspection object, to obtain corresponding inspection parameters; wherein the inspection objects include river inspection, mountain slope inspection, photovoltaic component inspection and substation equipment inspection Step 3, planning a path based on the three-dimensional digital map model of the hydroelectric station and the inspection parameters, to obtain inspection task data.

[0026] Firstly, the geographic spatial data of the entire hydropower station is collected by using the Beidou satellite positioning system, laser radar scanning and oblique photogrammetry technology, and a three-dimensional digital map model with centimeter-level precision is constructed. The model contains the accurate position information of the river profile, mountain slope terrain, photovoltaic cell component distribution, 110kV substation layout and all electrical equipment.

[0027] Secondly, differentiated inspection parameters are formulated according to the characteristics of different inspection objects: River inspection adopts a flight height of 30-50 meters, focusing on monitoring water level changes and river foreign objects; Mountain slope inspection adopts a 50-100 meter height of the ground flight mode, maintains a constant distance from the slope surface, and ensures the acquisition of complete slope shape data; Photovoltaic component inspection adopts low-altitude flight of 15-30 meters to perform S-shaped route full coverage scanning; Substation equipment inspection adopts 10-20 meter fine flight to hover and shoot at key equipment.

[0028] Finally, based on the path planning algorithm, the shortest flight distance, battery endurance, communication signal coverage and other constraint conditions are considered to automatically generate an optimized inspection route. The system integrates all the above parameters to form structured inspection task data, including complete information such as waypoint coordinates, flight height, speed, hovering time, gimbal angle, shooting mode, etc.

[0029] As can be seen, this step effectively reduces flight time and energy consumption through precise task planning. Through differentiated inspection strategies, the data collection quality of various types of inspection objects is significantly improved, and the monitoring accuracy of key areas is improved. Through automated task generation rather than manual planning, human errors are avoided.

[0030] S102, based on the inspection task data and the unmanned aerial vehicle multi-dimensional data acquisition device, unmanned aerial vehicle autonomous inspection data acquisition is performed to obtain inspection data; On the basis of S101, this step aims to perform unmanned aerial vehicle autonomous inspection data acquisition based on the inspection task data and the unmanned aerial vehicle multi-dimensional data acquisition device to obtain inspection data.

[0031] Among them, a single sensor cannot fully obtain the monitoring information of the complex environment of the hydropower station. By integrating multiple high-precision sensors, multi-dimensional and multi-modal data acquisition is achieved, which can obtain complementary information from different dimensions such as visible light, infrared and laser, improving the accuracy and reliability of anomaly detection. The autonomous inspection mode ensures the standardization and consistency of data acquisition.

[0032] Optionally, this step can include: The unmanned aerial vehicle is operated based on the inspection task data to perform autonomous cruising; and multi-dimensional data is collected by the multi-dimensional data collection device of the unmanned aerial vehicle to obtain the inspection data.

[0033] The multi-dimensional data collection device of the unmanned aerial vehicle includes a 4K high-definition visible light camera, an infrared thermal imager, a laser radar scanner, and a Beidou high-precision positioning module.

[0034] When performing the inspection, the system first performs automatic safety inspection before takeoff to confirm that the battery has sufficient power, the GPS signal is good, and the communication link is normal. Subsequently, the unmanned aerial vehicle automatically takes off according to the preset flight route in the inspection task data, and the flight control system adjusts the flight attitude in real time to adapt to changes in wind speed, air pressure, and other environmental changes.

[0035] During the flight, the multi-dimensional data collection device works synchronously: The high-definition visible light camera continuously shoots at a frame rate of 30 fps, automatically adjusts parameters such as exposure and white balance, and ensures clear images; the infrared thermal imager scans the temperature of electrical equipment with a temperature resolution of 0.05℃, which can accurately identify abnormal heating points; the laser radar scans the terrain at a rate of 1 million sampling points per second, generating high-density point cloud data; and the Beidou positioning module records the flight trajectory and shooting position in real time, with a positioning accuracy of better than 0.5 meters.

[0036] The collected data is transmitted in real time to the ground station through the 5G / 4G network, and the original data is saved in the on-board storage device. For areas with weak network signals, the system uses edge computing technology for data compression and key frame extraction, preferentially transmitting important information, and automatically supplementing the transmission of the remaining data after returning.

[0037] As can be seen, this step improves the accuracy of abnormal detection and reduces the false alarm rate through multi-dimensional data fusion collection. Through the autonomous inspection mode, the consistency and comparability of data collection are guaranteed, providing a reliable foundation for subsequent trend analysis. Through real-time data transmission, the discovery time of key risks is shortened to minutes, greatly improving the emergency response speed.

[0038] S103, intelligent identification and analysis of the inspection data based on the hydropower station multi-algorithm identification model to obtain a risk assessment report; wherein the hydropower station multi-algorithm identification model includes a personnel identification algorithm, a water area identification algorithm, and a device defect identification algorithm. On the basis of S102, this step aims to intelligently identify and analyze the inspection data based on the hydropower station multi-algorithm identification model to obtain a risk assessment report; wherein the hydropower station multi-algorithm identification model includes a personnel identification algorithm, a water area identification algorithm, and a device defect identification algorithm.

[0039] Considering the diverse types of risks faced by hydropower stations, including personnel intrusion, water level abnormalities, equipment failures, etc., a single algorithm cannot cover all scenarios. By deploying targeted multi-algorithm identification models, different types of risk identification tasks can be processed in parallel, improving the comprehensiveness and accuracy of identification. At the same time, by comprehensively analyzing the identification results of multiple algorithms, the risk level can be more accurately assessed.

[0040] Optionally, this step can include: The personnel identification algorithm is based on the YOLOv5 model of deep learning, trained on 100,000 hydropower station scene pictures, and can accurately identify personnel entering dangerous areas. The algorithm analyzes visible light images in real time, detects human contour features, and determines whether the personnel position is within the preset dangerous area, such as around high-voltage electrical equipment or near steep slopes.

[0041] The water area identification algorithm uses semantic segmentation technology and is based on the U-Net network architecture for pixel-level analysis of river images. The algorithm identifies the boundaries between water and shorelines, accurately measures water level positions, and compares them with historical water level data to calculate water level change rates. When detecting abnormal water level rise (such as an increase of more than 0.5 meters within 1 hour), an early warning is triggered. The equipment defect identification algorithm combines visible light and infrared image information and uses a multi-modal deep learning model. The algorithm can identify 12 common electrical equipment defects, including insulator flashover, damage, wire breakage, hardware corrosion, transformer oil leakage, etc. For temperature abnormalities, the algorithm analyzes the temperature distribution of infrared images to identify local hot spots, and alarms when the temperature difference exceeds the set threshold (such as a temperature difference of more than 10°C between similar devices). The three algorithms process the inspection data in parallel, each outputting identification results, and then the system performs comprehensive analysis: calculates the risk level (classified into general, larger, and major levels), determines the risk location (accurate to latitude and longitude coordinates), assesses the impact range, and predicts the development trend. Finally, a structured risk assessment report is generated, containing complete information such as risk type, location, level, evidence pictures, and disposal suggestions.

[0042]

[0043] ​​As can be seen, the risk detection rate of the step reaches more than 98% through multi-algorithm parallel identification, and the missing detection situation is basically eliminated. Through intelligent analysis instead of manual interpretation, the identification efficiency is improved by 20 times, and is not affected by subjective factors. Through the generation of a standardized risk assessment report, clear evidence is provided for subsequent early warning and disposal, and the decision-making efficiency is improved.

[0044] S104, early warning based on the risk assessment report; On the basis of S103, the step aims to early warning based on the risk assessment report.

[0045] Among them, timely and accurate early warning is the key to preventing accidents. According to the risk level and type in the risk assessment report, a hierarchical and classified early warning strategy can ensure that relevant personnel learn about the risk information in the first time and take appropriate disposal measures. The multi-channel early warning method ensures the reliability of information transmission.

[0046] The system automatically triggers a hierarchical early warning mechanism based on the risk assessment report: For general risks (such as minor equipment defects, individual personnel approaching the warning area, etc.), the system pushes a message to the on-duty personnel through the mobile APP, requiring them to pay special attention during the next routine inspection. The early warning information includes GPS coordinates of the risk location, on-site pictures, brief description, etc., and the on-duty personnel need to confirm receipt within 30 minutes.

[0047] For larger risks (such as water level close to the warning line, abnormal temperature rise of equipment, multiple people entering the danger zone, etc.), the system notifies the on-duty personnel and department heads through multiple channels such as SMS, APP push, email, etc. The early warning information is more detailed, including historical trend charts, possible consequence analysis, etc. Relevant personnel need to respond within 15 minutes and start the emergency plan.

[0048] For major risks (such as monitoring signs of landslides, rapid water level rise, equipment smoking and fire, etc.), the system immediately triggers an emergency warning, synchronously notifying the on-duty personnel, department heads and decision-making leaders through all available channels such as phone voice, SMS, APP pop-up window, etc. At the same time, it automatically starts the sound and light alarm and sends an alarm on site. The early warning information contains a real-time video link, supporting remote viewing of the on-site situation.

[0049] After the early warning is issued, the system continues to track the disposal progress, records the response time and disposal measures of each link, and forms a complete early warning response log. For early warnings that are not responded to in time, the system automatically upgrades the push range to ensure that the risk is properly disposed of.

[0050] As can be seen, this step realizes precise control of risks through a hierarchical early warning mechanism, avoiding the "Wolf Came" effect caused by excessive early warning. Through multi-channel push, the early warning delivery rate reaches 100%, and the average response time is shortened to within 5 minutes. Through real-time tracking and automatic escalation mechanism, it is ensured that all risks are disposed of in time, and the accident prevention rate is improved by 85%.

[0051] S105, the risk assessment report is archived.

[0052] On the basis of S104, this step aims to archive the risk assessment report.

[0053] Finally, the risk assessment report contains valuable historical data and experience information, which can form a risk knowledge base of the hydropower station through systematic archiving. These data can not only be used for post-analysis and responsibility tracing, but more importantly, they can provide data support for algorithm optimization, trend prediction and management improvement.

[0054] First, index by time dimension, each report is marked with accurate generation timestamp, support fast retrieval by year, month, day, hour. Second, classify by risk type, store different types of reports such as personnel intrusion, water level anomaly, equipment defect separately, facilitate comparative analysis of similar risks. Third, establish spatial index by risk location, associate reports with three-dimensional digital map, can visually display historical risk distribution on the map.

[0055] When archiving, the system automatically extracts the key information of the report, including risk type, level, location coordinates, identification algorithm, confidence, disposal result, etc., to form structured metadata. The original inspection images, videos and other evidence materials are stored in compressed form, but the original resolution backup is retained. All data adopts local server and cloud dual backup strategy, local saves recent 3 months of hot data for fast access, cloud saves all historical data.

[0056] Archived risk assessment reports are regularly analyzed by data mining: statistics of the occurrence frequency and distribution law of various risks, identification of high-risk areas; analyze the time distribution characteristics of risks, find seasonal and periodic rules; evaluate the effect of various disposal measures, optimize emergency plans. These analysis results are fed back to the inspection task planning and algorithm training, forming a continuous improvement closed loop.

[0057] As can be seen, this step forms a complete hydropower station risk database through systematic archiving. Through data mining analysis, several previously unknown risk patterns are discovered, such as the correlation between certain equipment defects and temperature, humidity. Through knowledge accumulation and experience summary, the risk prediction accuracy is improved, providing a scientific basis for preventive maintenance of hydropower stations.

[0058] In summary, the embodiment realizes precise monitoring and efficient management of the overall risk of the hydropower station by constructing an intelligent inspection system based on a three-dimensional digital map model of the hydropower station. Through scientific planning of the inspection task, the flight path is optimized, significantly improving the inspection efficiency and coverage. The use of the collaborative work of the multi-dimensional data collection equipment of the unmanned aerial vehicle realizes the fusion collection of multi-modal information such as visible light, infrared, and laser, greatly improving the accuracy and comprehensiveness of anomaly detection. The parallel processing mechanism of the multi-algorithm identification model of the hydropower station enables precise identification of multiple risks such as personnel intrusion, water level anomalies, and equipment defects, effectively avoiding the missed detection of safety hazards. The hierarchical early warning mechanism ensures the timely transmission of risk information, significantly shortening the emergency response time and improving the timeliness of risk disposal. Through the systematic archiving of the risk assessment report, a complete risk knowledge base is formed, providing reliable data support for trend analysis and preventive maintenance, thereby significantly improving the overall safety management level of the hydropower station and effectively ensuring the safe and stable operation of the hydropower station.

[0059] The following describes a hydropower station unmanned aerial vehicle intelligent inspection system provided by an embodiment of the present application. The hydropower station unmanned aerial vehicle intelligent inspection system described below can correspond to the hydropower station unmanned aerial vehicle intelligent inspection method described below.

[0060] Please refer to Figure 2 , Figure 2 The following describes a hydropower station unmanned aerial vehicle intelligent inspection system provided by an embodiment of the present application. The hydropower station unmanned aerial vehicle intelligent inspection system described below can correspond to the hydropower station unmanned aerial vehicle intelligent inspection method described below.

[0061] In this embodiment, the system can include: The task planning module 100 is configured to plan an inspection task based on a three-dimensional digital map model of the hydropower station and object characteristic data of the inspection task, and obtain inspection task data. The unmanned aerial vehicle inspection module 200 is configured to perform autonomous inspection data collection of the unmanned aerial vehicle based on the inspection task data and multi-dimensional data collection equipment of the unmanned aerial vehicle, and obtain inspection data. The inspection analysis module 300 is configured to perform intelligent identification and analysis of the inspection data based on a multi-algorithm identification model of the hydropower station, and obtain a risk assessment report. The multi-algorithm identification model of the hydropower station includes a personnel identification algorithm, a water area identification algorithm, and an equipment defect identification algorithm. The inspection early warning module 400 is configured to perform early warning based on the risk assessment report. The data archiving module 500 is configured to archive the risk assessment report.

[0062] Optionally, the task planning module is specifically configured to construct a map model based on geographic information data of the hydropower station, high-precision coordinate data, and the labeled inspection key area, to obtain a three-dimensional digital map model of the hydropower station; perform inspection parameter equipment based on the three-dimensional digital map model of the hydropower station and environmental characteristic data of each inspection object, to obtain corresponding inspection parameters; wherein the inspection object includes river inspection, mountain slope inspection, photovoltaic component inspection, and substation equipment inspection; perform path planning based on the three-dimensional digital map model of the hydropower station and the inspection parameters, to obtain inspection task data.

[0063] Optionally, the unmanned aerial vehicle inspection module is specifically configured to operate the unmanned aerial vehicle to perform autonomous cruising based on the inspection task data; perform multi-dimensional data collection by using a multi-dimensional data collection device of the unmanned aerial vehicle, to obtain inspection data.

[0064] Optionally, the inspection analysis module is specifically configured to identify personnel in a dangerous area in the inspection data by using a personnel identification algorithm, to obtain personnel abnormal features; identify water area abnormalities in the inspection data by using a water area identification algorithm, to obtain water area abnormal features; identify equipment defects in the inspection data by using an equipment defect identification algorithm, to obtain equipment abnormal features; and generate a risk assessment report based on the personnel abnormal features, the water area abnormal features, and the equipment abnormal features.

[0065] The application also provides a hydropower station unmanned aerial vehicle intelligent inspection device, please refer to Figure 3 , Figure 3 The application provides a hydropower station unmanned aerial vehicle intelligent inspection device, and a structure diagram of the hydropower station unmanned aerial vehicle intelligent inspection device is as follows. The memory is used to store a computer program. The processor is used to execute the computer program, and can realize the steps of any one of the above hydropower station unmanned aerial vehicle intelligent inspection methods.

[0066] As shown in the following, Figure 3 A structure diagram of the hydropower station unmanned aerial vehicle intelligent inspection device is as follows. The hydropower station unmanned aerial vehicle intelligent inspection device can include a processor 10, a memory 11, a communication interface 12, and a communication bus 13. The processor 10, the memory 11, and the communication interface 12 can communicate with each other through the communication bus 13.

[0067] In the embodiment of the application, the processor 10 can be a central processing unit (CPU), an application specific integrated circuit, a digital signal processor, a field programmable gate array, or other programmable logic devices.

[0068] The processor 10 can call a program stored in the memory 11. Specifically, the processor 10 can execute the operations in the embodiment of the abnormal IP identification method.

[0069] The memory 11 stores one or more programs, which can include program codes including computer operation instructions. In the embodiment of the present application, the memory 11 stores at least programs for implementing the following functions: planning a patrol task based on a three-dimensional digital map model of the hydropower station and object characteristic data of the patrol task to obtain patrol task data; performing autonomous patrol data collection of the unmanned aerial vehicle based on the patrol task data and a multi-dimensional data collection device of the unmanned aerial vehicle to obtain patrol data; performing intelligent identification analysis on the patrol data based on a multi-algorithm identification model of the hydropower station to obtain a risk assessment report, wherein the multi-algorithm identification model of the hydropower station includes a personnel identification algorithm, a water area identification algorithm, and a device defect identification algorithm; performing early warning based on the risk assessment report; filing the risk assessment report.

[0070] In a possible implementation, the memory 11 can include a program storage area and a data storage area. The program storage area can store an operating system and at least one application required by a function, etc. The data storage area can store data created during use.

[0071] In addition, the memory 11 can include a high-speed random access memory and can also include a non-volatile memory, such as at least one magnetic disk storage device or other volatile solid-state storage device.

[0072] The communication interface 12 can be an interface of a communication module, which is used to connect with other devices or systems.

[0073] Of course, it should be noted that Figure 3 the structures shown do not constitute a limitation on the hydropower station unmanned aerial vehicle intelligent patrol device in the embodiment of the present application. In actual applications, the hydropower station unmanned aerial vehicle intelligent patrol device can include more or fewer components than those shown or can combine certain components. Figure 3

[0074] The present application also provides a computer readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of any one of the above hydropower station unmanned aerial vehicle intelligent patrol methods can be implemented.

[0075] The computer readable storage medium can include a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0076] ​The computer readable storage medium provided in the present application is described above with reference to the method embodiments, and the present application will not be repeated here.

[0077] The embodiments in the specification are described progressively, and each embodiment focuses on the difference from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the related parts can be referred to the method part.

[0078] The skilled person can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0079] The steps of the method or algorithm described in combination with the embodiments disclosed herein can be directly implemented by hardware, a software module executed by a processor, or a combination of both. The software module can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0080] The water power station unmanned aerial vehicle intelligent inspection method, the water power station unmanned aerial vehicle intelligent inspection system, the water power station unmanned aerial vehicle intelligent inspection device, and the computer readable storage medium provided by the present application are described in detail. The principles and implementation modes of the present application are described by applying specific examples. The above embodiment description is only used to help understand the method and its core idea of the present application. It should be pointed out that for ordinary skilled person in the technical field, without departing from the principles of the present application, some improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope of the claims of the present application.

Claims

1. A method for intelligent inspection of a hydroelectric power station by a drone, characterized in that, The method comprises the following steps: planning a patrol task based on a three-dimensional digital map model of a hydropower station and object characteristic data, to obtain patrol task data; autonomous patrol data collection by a UAV based on the patrol task data and a multi-dimensional data collection device of the UAV, to obtain patrol data; intelligent identification and analysis of the patrol data based on a multi-algorithm identification model of the hydropower station, to obtain a risk assessment report; wherein the multi-algorithm identification model of the hydropower station comprises a personnel identification algorithm, a water area identification algorithm, and a device defect identification algorithm; warning based on the risk assessment report; filing the risk assessment report.

2. The method of claim 1, wherein, The method comprises the following steps: constructing a map model based on geographic information data, high-precision coordinate data, and marked key areas for inspection of the hydropower station, to obtain the three-dimensional digital map model of the hydropower station; planning a patrol parameter device based on the three-dimensional digital map model of the hydropower station and environmental characteristic data of each patrol object, to obtain corresponding patrol parameters; wherein the patrol objects comprise riverway inspection, mountain slope inspection, photovoltaic component inspection, and substation device inspection planning a path based on the three-dimensional digital map model of the hydropower station and the patrol parameters, to obtain the patrol task data.

3. The method of claim 2, wherein, The method comprises the following steps: autonomously cruising the UAV based on the patrol task data; collecting multi-dimensional data by the multi-dimensional data collection device of the UAV, to obtain the patrol data.

4. The method of claim 3, wherein, The method comprises the following steps: identifying personnel in a dangerous area in the patrol data by the personnel identification algorithm, to obtain personnel abnormal features; identifying water area abnormalities in the patrol data by the water area identification algorithm, to obtain water area abnormal features; identifying device defects in the patrol data by the device defect identification algorithm, to obtain device abnormal features; generating a risk assessment report based on the personnel abnormal features, the water area abnormal features, and the device abnormal features.

5. An unmanned aerial vehicle intelligent inspection system for a hydropower station, characterized in that, The method comprises the following steps: a task planning module for planning a patrol task based on a three-dimensional digital map model of a hydropower station and object characteristic data, to obtain patrol task data; a UAV patrol module for autonomous patrol data collection by a UAV based on the patrol task data and a multi-dimensional data collection device of the UAV, to obtain patrol data; a patrol analysis module for intelligent identification and analysis of the patrol data based on a multi-algorithm identification model of the hydropower station, to obtain a risk assessment report; wherein the multi-algorithm identification model of the hydropower station comprises a personnel identification algorithm, a water area identification algorithm, and a device defect identification algorithm; a patrol warning module for warning based on the risk assessment report; a data filing module for filing the risk assessment report.

6. The intelligent inspection system of unmanned aerial vehicle for hydropower station of claim 5, wherein, The task planning module is specifically configured to perform map model construction based on geographic information data of the hydropower station, high-precision coordinate data, and labeled inspection key areas, to obtain a three-dimensional digital map model of the hydropower station. Based on the three-dimensional digital map model of the hydropower station and environmental characteristic data of each inspection object, inspection parameter equipment is performed to obtain corresponding inspection parameters; the inspection object includes river inspection, mountain slope inspection, photovoltaic component inspection, and substation equipment inspection.

7. The intelligent inspection system of unmanned aerial vehicle for hydropower station of claim 6, wherein, Based on the three-dimensional digital map model of the hydropower station and the inspection parameters, path planning is performed to obtain the inspection task data.

8. The intelligent inspection system of claim 7, wherein, The unmanned aerial vehicle inspection module is specifically configured to operate an unmanned aerial vehicle to perform autonomous cruising based on the inspection task data; and perform multi-dimensional data collection through the multi-dimensional data collection device of the unmanned aerial vehicle to obtain the inspection data. The inspection analysis module is specifically configured to identify personnel in a dangerous area in the inspection data through the personnel identification algorithm to obtain personnel abnormal features; identify water area abnormalities in the inspection data through the water area identification algorithm to obtain water area abnormal features; and identify equipment defects in the inspection data through the equipment defect identification algorithm to obtain equipment abnormal features.

9. A hydroelectric power station unmanned aerial vehicle intelligent inspection device, characterized in that, A risk assessment report is generated based on the personnel abnormal features, the water area abnormal features, and the equipment abnormal features. The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the hydropower station unmanned aerial vehicle intelligent inspection method. The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the hydropower station unmanned aerial vehicle intelligent inspection method.

10. A computer-readable storage medium, characterized in that, ​

Images