Unmanned aerial vehicle data processing method and system for key indicators of petroleum and natural gas inspection

Abstract

The present application relates to the technical field of oil and gas inspection, and particularly relates to a UAV data processing method and system for key indicators of oil and gas inspection. The method comprises the following steps: dividing an oil and gas inspection sub-region, dynamically adjusting the inspection priority of the inspection sub-region according to collected data; dynamically adjusting the current inspection route based on the inspection priority, and cooperatively scheduling multiple UAVs, synchronously updating the inspection state, and uploading the inspection data in real time; assigning corresponding priority queues to the inspection data according to the inspection priority for data processing, determining the abnormal level of the inspection sub-region in combination with the key indicators of oil and gas, and issuing a graded warning. The system comprises the following modules: a regional inspection priority adjustment module, a task dynamic planning module, and a data processing priority adaptation module. The inspection priority of the inspection sub-region is dynamically adjusted, multiple UAVs are cooperatively scheduled to upload the inspection data in real time, and a graded warning is issued according to the abnormal level of the inspection sub-region, thereby improving the efficiency of danger investigation.

Description

Technical Field

[0001] This invention relates to the field of oil and gas inspection technology, and in particular to a method and system for processing key indicators of oil and gas inspection using unmanned aerial vehicles (UAVs). Background Technology

[0002] The safe operation of the oil and gas industry relies heavily on the efficient identification and handling of key indicators such as equipment defects, media leaks, and environmental risks within the inspection area.

[0003] Currently, most drone-based oil and gas inspection data processing methods use a fixed pattern of processing data according to the order of collection time or the coverage area of ​​the flight route. This results in a lag in data processing in high-risk areas. Although existing drone data management platforms (such as airport data management centers) support multi-drone collaborative inspections, cloud-based data archiving, and basic AI analysis (such as fire identification in environmental monitoring), they do not prioritize inspection areas based on the risk differences of oil and gas facilities. This causes inspection data from high-risk areas (such as high-pressure pipeline sections and facilities around densely populated areas) to be processed concurrently with data from low-risk areas (such as pipeline sections in remote deserts), delaying the opportunity for hazard investigation and thus reducing the efficiency of hazard investigation. Summary of the Invention

[0004] The purpose of this invention is to provide a UAV data processing method and system for key indicators of oil and gas inspection, aiming to solve the technical problem in the prior art where inspection data from high-risk areas and low-risk areas are processed in a simultaneous queue, delaying the opportunity for hazard investigation and thus reducing the efficiency of hazard investigation.

[0005] To achieve the above objectives, the present invention employs a UAV data processing method for key indicators of oil and gas inspection, comprising the following steps:

[0006] Divide the oil and gas inspection sub-regions, collect environmental and equipment status data of the inspection sub-regions in real time, and dynamically adjust the inspection priority of the inspection sub-regions based on the collected data.

[0007] The current inspection route is dynamically adjusted based on the inspection priority, and multiple drones are coordinated and dispatched to update the inspection status synchronously and upload the inspection data in real time.

[0008] Based on the inspection priority, the inspection data is assigned to a corresponding priority queue for data processing. Combined with key oil and gas indicators, the anomaly level of the inspection sub-area is determined, and graded early warnings are issued.

[0009] Among the steps, the process of dividing the oil and gas inspection sub-regions, collecting real-time environmental and equipment status data for each sub-region, and dynamically adjusting the inspection priority of each sub-region based on the collected data is as follows:

[0010] Obtain map data of the oil and gas inspection area, divide the overall inspection area into multiple independent inspection sub-areas, and assign a unique identifier code to each sub-area;

[0011] Set an initial flight path, configure drones for each inspection sub-area, and conduct inspections of each sub-area according to the initial flight path, collecting environmental data and equipment status data in real time.

[0012] The system presets priority division rules, adjusts the priority of sub-regions based on the collected data, and outputs the adjustment results.

[0013] The process includes setting an initial flight path, configuring drones for each inspection sub-area, and conducting inspections of each sub-area according to the initial flight path, while collecting environmental and equipment status data in real time.

[0014] The environmental and equipment status data collected from each sub-region are obtained, and the data is cleaned and preliminarily classified.

[0015] Among them, in the steps of setting a preset priority division rule, adjusting the priority of sub-regions based on the collected data, and outputting the adjustment results:

[0016] If the priority is adjusted, the task attribute labels of the sub-region will be updated synchronously.

[0017] Among the steps, the following steps are involved: dynamically adjusting the current inspection route based on inspection priority, coordinating and scheduling multiple drones, synchronously updating the inspection status, and uploading inspection data in real time:

[0018] Retrieve the initial routes of each inspection sub-area, dynamically optimize the routes according to the inspection priority, and output the current inspection route adjustment data.

[0019] Based on the priority of each sub-region and the optimized route, multi-UAV collaborative scheduling is carried out;

[0020] The system can acquire real-time flight progress, data collection volume, and equipment status of drones during inspection missions, and update the execution status of inspection missions in each sub-area.

[0021] Continuously collect environmental and equipment status data for each sub-region and identify abnormal situations.

[0022] In the step of coordinating multi-UAV scheduling based on the priority of each sub-region and the optimized route:

[0023] Build an initial drone resource pool, establish a real-time updated drone resource pool, and record information on all drones currently available for inspection;

[0024] Determine the drone requirements for each inspection sub-area, dynamically adjust the flight path parameters and inspection priorities for each inspection sub-area, and calculate the number of drones required for each sub-area, the drone type requirements, and the estimated inspection time.

[0025] Initial allocation of drone resources: Based on the information from the drone resource pool and the needs of each sub-region, drones are initially allocated from the resource pool to each inspection sub-region.

[0026] Monitor the supply and demand balance of drone resources, monitor the drone resource usage and task progress in each inspection sub-area in real time, and trigger the resource rescheduling mechanism.

[0027] Dynamically adjust drone scheduling; for high-priority sub-regions that trigger the resource rescheduling mechanism, select idle drones and send task adjustment instructions to the idle drones.

[0028] To avoid conflicts and optimize routes, the flight paths of drones were replanned, and their flight altitudes and sequences were adjusted. The flight paths of drones were also optimized in conjunction with the inspection progress of each sub-area.

[0029] The process includes steps such as avoiding conflicts and optimizing routes, replanning flight paths for drones, adjusting flight altitudes and flight sequences, and optimizing drone flight paths based on the inspection progress of each sub-area:

[0030] Real-time feedback of scheduling results, recording the entire process of multi-UAV collaborative scheduling, and real-time updates of the task status and inspection sub-area information of each UAV.

[0031] Among these steps, the continuous collection of environmental and equipment status data for each sub-region and the identification of abnormal situations include:

[0032] If the drone detects an anomaly during the inspection, it will trigger a priority data collection request, extend the hovering time at that location, collect additional high-definition images and multi-dimensional sensor data, and simultaneously mark and upload the data.

[0033] Among them, the steps of allocating corresponding priority queues to the inspection data according to the inspection priority for data processing, determining the anomaly level of the inspection sub-area in combination with key oil and gas indicators, and issuing graded early warnings are as follows:

[0034] Construct a three-level data processing queue corresponding to the inspection priority, and receive inspection data;

[0035] Differentiated data processing strategies are adopted for different priority queues, and the anomaly level of each inspection sub-area is determined by combining key indicators of oil and gas inspection.

[0036] Implement tiered early warning systems based on anomaly level and inspection priority.

[0037] This invention also provides a UAV data processing system for key indicators of oil and gas inspection, including a regional inspection priority adjustment module, a task dynamic planning module, and a data processing priority adaptation module; wherein:

[0038] The regional inspection priority adjustment module is used to divide the oil and gas inspection sub-regions, collect environmental and equipment status data of the inspection sub-regions in real time, and dynamically adjust the inspection priority of the inspection sub-regions based on the collected data.

[0039] The task dynamic planning module is used to dynamically adjust the current inspection route based on the inspection priority, coordinate and schedule multiple UAVs, update the inspection status synchronously, and upload the inspection data in real time.

[0040] The data processing priority adaptation module is used to allocate corresponding priority queues to the inspection data according to the inspection priority for data processing, determine the anomaly level of the inspection sub-area in combination with key oil and gas indicators, and issue graded warnings.

[0041] This invention discloses a UAV data processing method and system for key indicators of oil and gas inspection. The method comprises a regional inspection priority adjustment module, a task dynamic planning module, and a data processing priority adaptation module, performing the following steps: dividing the oil and gas inspection into sub-regions; collecting environmental and equipment status data of the sub-regions in real time; dynamically adjusting the inspection priority of the sub-regions based on the collected data; dynamically adjusting the current inspection route based on the inspection priority; coordinating and scheduling multiple UAVs to synchronously update the inspection status and upload inspection data in real time; assigning corresponding priority queues to the inspection data according to the inspection priority for data processing; determining the anomaly level of the inspection sub-region based on key oil and gas indicators; and issuing graded warnings. By dynamically adjusting the inspection priority of the sub-regions, coordinating and scheduling multiple UAVs to upload inspection data in real time, and issuing graded warnings based on the anomaly level of the inspection sub-regions, the efficiency of hazard investigation is improved. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart of the steps of the UAV data processing method for key indicators of oil and gas inspection according to the present invention.

[0044] Figure 2 This is a flowchart of steps S100 of the present invention.

[0045] Figure 3 This is a flowchart of steps S200 of the present invention.

[0046] Figure 4 This is a flowchart of steps S202 of the present invention.

[0047] Figure 5 This is a flowchart of steps S300 of the present invention.

[0048] Figure 6 This is a schematic diagram of the structure of the UAV data processing system for key indicators of oil and gas inspection according to the present invention.

[0049] Figure 7 This is a schematic diagram of the electronic device of the present invention.

[0050] 401 - Area Inspection Priority Adjustment Module, 402 - Task Dynamic Planning Module, 403 - Data Processing Priority Adaptation Module. Detailed Implementation

[0051] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0052] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0053] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0054] Please see Figures 1-5 This invention provides a method for processing key indicators of oil and gas inspection data using unmanned aerial vehicles (UAVs), comprising the following steps:

[0055] S100: Divide the oil and gas inspection sub-areas, collect environmental and equipment status data of the inspection sub-areas in real time, and dynamically adjust the inspection priority of the inspection sub-areas based on the collected data.

[0056] In this embodiment, oil and gas inspection sub-regions are divided, and environmental and equipment status data of these sub-regions are collected in real time. The inspection priority of each sub-region is dynamically adjusted based on the collected data. The specific process is as follows:

[0057] S101: Obtain map data of the oil and gas inspection area, divide the overall inspection area into multiple independent inspection sub-areas, and assign a unique identifier code to each sub-area;

[0058] S102: Set the initial flight path, configure drones for each inspection sub-area, and conduct inspections of each sub-area according to the initial flight path, collecting environmental data and equipment status data in real time.

[0059] S103: Acquire environmental and equipment status data collected from each sub-region, and clean and preliminarily classify the data respectively;

[0060] S104: Preset priority division rules, adjust the inspection priority of sub-areas according to the collected data, and output the adjustment status. If there is an adjustment in the inspection priority, the task attribute label of the sub-area will be updated synchronously.

[0061] During the aforementioned process, based on the cloud service platform of the drone data management center, a GIS map of the oil and gas inspection area is imported, including basic information such as pipeline routes, station locations, and storage distribution. Combined with facility characteristics (pipeline design pressure, equipment operating years, historical fault records) and environmental features (surrounding population density, distance to sensitive areas), the overall inspection area is divided into multiple independent inspection sub-areas. Each sub-area is assigned a unique identifier code and simultaneously entered into the platform's plan database for management. Suitable drone models are configured for each inspection sub-area. The drones are equipped with visible light cameras, infrared thermal imagers, gas sensors (for oil and gas leak detection), and IoT data acquisition modules. They inspect each sub-area according to a preset initial flight path, collecting real-time environmental data (temperature, humidity, meteorological conditions, combustible gas concentration) and equipment status data (pipeline appearance, valve sealing, equipment operating temperature).

[0062] Through the operation mode of the UAV data management center, the environmental and equipment status data collected from each sub-area are uploaded to the cloud platform data management module via the MQTT protocol. Blurry images and abnormal sensor values ​​are removed from the data, and the data is initially classified according to the labels "environmental data" and "equipment data".

[0063] Based on the collected data after cleaning, and combined with the preset priority classification rules (high-risk sub-area judgment criteria: pipeline pressure ≥10MPa, equipment operation years ≥15 years, surrounding population density ≥500 people / square kilometer, combustible gas concentration close to the safety threshold, etc.; medium-risk sub-area: single high-risk characteristic; low-risk sub-area: no high-risk characteristics), the initial inspection priority (high, medium, and low levels) is assigned to each inspection sub-area; in subsequent inspections, if the collected data of a certain sub-area changes in real time (such as sudden rainstorm, sudden rise in equipment temperature, or gas concentration exceeding the standard), the platform automatically triggers priority adjustment and synchronously updates the task attribute tags of the corresponding sub-area in the plan library.

[0064] S200: Based on inspection priority, it dynamically adjusts the current inspection route, coordinates and dispatches multiple UAVs, updates the inspection status synchronously, and uploads inspection data in real time.

[0065] In this implementation, the current inspection route is dynamically adjusted based on inspection priority, and multiple UAVs are coordinated and scheduled to synchronously update the inspection status and upload inspection data in real time. The specific process is as follows:

[0066] S201: Retrieve the initial routes of each inspection sub-area, dynamically optimize the routes according to the inspection priority, and output the current inspection route adjustment data;

[0067] S202: Conduct multi-UAV collaborative scheduling based on the priority of each sub-region and the optimized route;

[0068] S203: Real-time acquisition of the drone's flight progress, data collection volume, and equipment status during the inspection mission, and updating the execution status of the inspection mission in each sub-area;

[0069] S204: Continuously collect environmental and equipment status data for each sub-area and identify abnormal situations; if the drone finds an abnormal situation during the inspection, it will trigger a key collection request, extend the hovering time at that point, supplement the collection of high-definition images and multi-dimensional sensor data, and simultaneously mark and upload the data.

[0070] Furthermore, in the step of collaborative scheduling of multiple UAVs based on the priority of each sub-region and the optimized route:

[0071] S2021: Build an initial drone resource pool, establish a real-time updated drone resource pool, and record information on all drones currently available for inspection;

[0072] S2022: Determine the drone requirements for each inspection sub-area, dynamically adjust the flight path parameters and inspection priorities for each inspection sub-area, and calculate the number of drones required, the model requirements, and the estimated inspection time for each sub-area.

[0073] S2023: Initial allocation of drone resources. Based on the information of the drone resource pool and the needs of each sub-region, drones are initially allocated from the resource pool to each inspection sub-region.

[0074] S2024: Monitor the supply and demand balance of drone resources, monitor the drone resource usage and task progress in each inspection sub-area in real time, and trigger the resource rescheduling mechanism;

[0075] S2025: Dynamically adjust drone scheduling. For high-priority sub-areas that trigger the resource rescheduling mechanism, select idle drones and send task adjustment instructions to the idle drones.

[0076] S2026: Avoid conflicts and optimize paths. Re-plan the flight paths of drones, adjust their flight altitude and flight sequence, and optimize the drone flight paths in combination with the inspection progress of each sub-area.

[0077] S2027: Real-time feedback of scheduling results, recording the entire process of multi-UAV collaborative scheduling, and real-time updates of the task status and inspection sub-area information of each UAV.

[0078] In the above process, the initial routes for each inspection sub-area are retrieved from the route database of the UAV data management center, and the routes are dynamically optimized in combination with the inspection priorities determined in step S100:

[0079] High-priority sub-areas adopt a dense flight path + high-frequency data collection strategy (flight path spacing ≤ 50m, drone hovering data collection frequency ≥ 2 times / km, focusing on covering key parts of the equipment).

[0080] The medium-priority sub-area adopts a standard route + conventional data collection strategy (route spacing 50~100m, data collection frequency 1 time / km).

[0081] Low-priority sub-regions adopt a sparse flight path + low-frequency data collection strategy (flight path spacing ≥ 100m, data collection frequency 1 time / 2km).

[0082] The optimized routes are synchronously stored in the route database.

[0083] Through the cloud platform's task planning and management module, multi-UAV collaborative scheduling is carried out based on the priority of each sub-region and the optimized flight path. The specific process is as follows:

[0084] Construct an initial drone resource pool: In the task planning and management module of the drone data management center cloud platform, establish a real-time updated drone resource pool to record information on all drones currently available for inspection, including model, current status (idle, performing a task, awaiting maintenance), remaining flight time, type of onboard sensors (visible light camera, infrared thermal imager, gas sensor, etc.), and location. The resource pool information is synchronized to the platform's operation mode module in real time to ensure that the latest drone status can be obtained during scheduling.

[0085] Determine the drone requirements for each inspection sub-area: Based on the dynamically adjusted flight path parameters (flight length, data collection frequency, number of key points, etc.) and inspection priority of each inspection sub-area in step S200, calculate the required number of drones, drone model requirements, and estimated inspection time for each sub-area. High-priority sub-areas will be prioritized for drones with long endurance and multi-sensor carrying capabilities, and the required number of drones will be configured at 1.2 times the flight path complexity and data collection workload to handle potential emergencies. Medium and low-priority sub-areas will be configured with appropriate drone models and quantities based on actual needs.

[0086] Initial allocation of drone resources: Based on the information from the drone resource pool and the needs of each sub-region, drones are initially allocated from the resource pool to each inspection sub-region. Idle, compatible drones are prioritized for allocation to high-priority sub-regions to ensure they can quickly initiate inspection tasks. For medium and low-priority sub-regions, the remaining compatible drone resources are allocated sequentially, provided the needs of high-priority sub-regions are met. The allocation results are recorded in the platform's plan library, noting the sub-region identifier and task start time for each drone.

[0087] Monitoring the supply and demand balance of drone resources: During the execution of inspection tasks, the platform monitors the usage of drone resources and task progress in each inspection sub-area in real time. When a drone in a high-priority sub-area is unable to continue its task due to malfunction, insufficient power, or other reasons, or when the existing drone resources are insufficient due to a temporary increase in the workload, a resource rescheduling mechanism is triggered. At the same time, the status of drones in medium- and low-priority sub-areas is tracked in real time, and information on drones that are idle or whose tasks are about to be completed is recorded.

[0088] Dynamic adjustment of drone scheduling: For high-priority sub-areas that trigger the resource rescheduling mechanism, available idle drones or drones that can end their current tasks early are selected from sub-areas where the task progress is nearing completion or the priority is low. The platform sends task adjustment instructions to these drones and re-plans their routes to the high-priority sub-areas that need support. If the inspection tasks of the medium and low-priority sub-areas originally handled by the reassigned drones are not completed, they will be supplemented and allocated when there are new idle drones in the resource pool, or delayed until the completion of subsequent batches, to ensure that the inspection tasks of high-priority sub-areas are not affected.

[0089] Conflict Avoidance and Path Optimization: During multi-UAV collaborative scheduling, the platform's flight path database module monitors the flight trajectories of each UAV in real time. A spatial conflict detection algorithm (based on UAV real-time location and flight path planning) identifies potential conflict risks such as intersecting flight paths and close-range flight. When a conflict risk is detected, the platform automatically replans flight paths for the relevant UAVs, adjusting their flight altitude and sequence to ensure a safe distance (≥50 meters) between them, thus preventing collisions. Simultaneously, based on the inspection progress of each sub-area, the platform optimizes UAV flight paths, reducing unnecessary back-and-forth flights and improving overall inspection efficiency.

[0090] Real-time feedback of scheduling results: The entire process of multi-UAV collaborative scheduling (including initial allocation, dynamic adjustment, conflict handling, etc.) is recorded in the platform's plan library and log system, updating the task status of each UAV (in progress, allocated, task completed, etc.) and corresponding inspection sub-area information in real time. Managers can view the scheduling results through the platform's visual interface, including the UAV configuration, task progress, flight trajectory, etc. of each sub-area, facilitating timely monitoring of inspection dynamics and manual intervention (such as manual scheduling in special circumstances).

[0091] During the inspection missions of drones, the flight progress (percentage of completed routes), data collection volume, and equipment status (battery power, sensor operation status) of each drone are acquired in real time. This information is then synchronized to the plan database, and the execution status of each sub-area inspection mission is updated according to "pending execution", "in execution (priority marked)", "completed" and "paused (equipment failure, etc.)".

[0092] When the drone is conducting inspections along a dynamically adjusted route, it continuously collects environmental and equipment status data for each sub-area. The collected data is appended with "sub-area identifier + priority label + collection timestamp" and uploaded in real time via HTTP or WebSocket protocol (link encrypted with TLS). If a drone detects a suspected anomaly during inspection (such as pipeline corrosion images or abnormal fluctuations in gas concentration), it automatically triggers a "key collection" command, extending the hovering time at that location to collect additional high-definition images and multi-dimensional sensor data. The data is then simultaneously marked as "suspected anomaly" and uploaded with priority.

[0093] S300: Based on the inspection priority, the inspection data is assigned to a corresponding priority queue for data processing. Combined with key oil and gas indicators, the anomaly level of the inspection sub-area is determined, and a graded warning is issued.

[0094] In this implementation, inspection data is assigned to corresponding priority queues for data processing based on inspection priorities. The anomaly level of the inspected sub-area is determined by combining key oil and gas indicators, and tiered early warnings are issued. The specific process is as follows:

[0095] S301: Construct a three-level data processing queue corresponding to the inspection priority, and receive inspection data;

[0096] S302: Differentiated data processing strategies are adopted for different priority queues, and the anomaly level of each inspection sub-area is determined by combining key indicators of oil and gas inspection.

[0097] S303: Implement graded early warning based on anomaly level and inspection priority.

[0098] In the above process, in the data management module of the UAV data management center cloud platform, a three-level data processing queue (high priority queue, medium priority queue, and low priority queue) corresponding to the inspection priority is constructed. After receiving the inspection data uploaded in step S200, it is allocated to the corresponding queue according to the "priority tag" attached to the data. The capacity of the high priority queue accounts for ≥40%, and it occupies the platform's computing resources first.

[0099] Differentiated data processing strategies are adopted for queues with different priorities:

[0100] High-priority queue data uses a deep analysis mode, calling the oil and gas AI model in the platform's model library to perform pixel-level detection and multi-dimensional analysis of the data;

[0101] The medium-priority queue data uses standard analysis mode and AI model to perform feature-level detection (such as whether the device appearance is normal and whether the gas concentration is within the safe range).

[0102] Low-priority queue data is processed using a fast analysis mode, which only performs basic feature identification (such as whether there are obvious obstacles or whether environmental parameters meet the standards), and then in-depth analysis is performed during non-working hours.

[0103] Combining key indicators for oil and gas inspections (equipment status indicators: pipeline corrosion level, valve sealing failure; media leakage indicators: combustible gas leakage concentration, leakage range; environmental safety indicators: surrounding combustible gas concentration, impact of meteorological conditions on facilities), the abnormality level of each inspection sub-area is determined based on the data processing results: critical abnormality (such as gas leakage concentration exceeding the standard, pipeline rupture, etc., which may cause safety accidents), serious abnormality (such as moderate equipment corrosion, minor valve leakage, etc., which require immediate handling), general abnormality (such as minor stains on equipment surface, slight fluctuations in environmental parameters, etc., which can be temporarily postponed), and no abnormality.

[0104] A tiered early warning system is implemented based on anomaly level and inspection priority: For high-priority sub-areas with critical anomalies, early warning information is pushed via SMS, platform pop-ups, and API interfaces (connected to oil and gas company emergency systems), along with GIS coordinates of the anomaly sub-area, on-site images / videos (accessed from media library data), and handling suggestions, with a response time of ≤5 minutes; For high-priority sub-areas with severe anomalies or medium-priority sub-areas with critical anomalies, early warnings are pushed via SMS and platform pop-ups, with a response time of ≤15 minutes; For other anomaly combinations, early warnings are pushed via platform messages, with a response time of ≤30 minutes, and early warning records are synchronized to the planning and media libraries.

[0105] Corresponding to the aforementioned embodiments of the UAV data processing method for key indicators of oil and gas inspection, this application also provides embodiments of the UAV data processing system for key indicators of oil and gas inspection.

[0106] Figure 6 This is a block diagram of a drone data processing system for key indicators of oil and gas inspection, according to an exemplary embodiment. (Refer to...) Figure 6 The system may include: a regional inspection priority adjustment module 401, a task dynamic planning module 402, and a data processing priority adaptation module 403; wherein:

[0107] The regional inspection priority adjustment module 401 is used to divide the oil and gas inspection sub-regions, collect environmental and equipment status data of the inspection sub-regions in real time, and dynamically adjust the inspection priority of the inspection sub-regions based on the collected data.

[0108] The task dynamic planning module 402 is used to dynamically adjust the current inspection route based on the inspection priority, coordinate and schedule multiple UAVs, update the inspection status synchronously, and upload the inspection data in real time.

[0109] The data processing priority adaptation module 403 is used to allocate corresponding priority queues to the inspection data according to the inspection priority for data processing, determine the anomaly level of the inspection sub-area in combination with key oil and gas indicators, and issue graded warnings.

[0110] In this embodiment, the regional inspection priority adjustment module 401 divides the oil and gas inspection sub-regions, collects environmental and equipment status data of the inspection sub-regions in real time, and dynamically adjusts the inspection priority of the inspection sub-regions based on the collected data; the task dynamic planning module 402 dynamically adjusts the current inspection route based on the inspection priority, coordinates and schedules multiple UAVs, updates the inspection status synchronously, and uploads inspection data in real time; the data processing priority adaptation module 403 assigns corresponding priority queues to the inspection data according to the inspection priority for data processing, determines the anomaly level of the inspection sub-regions in conjunction with key oil and gas indicators, and issues graded warnings; by dynamically adjusting the inspection priority of the inspection sub-regions, coordinating and scheduling multiple UAVs to upload inspection data in real time, and issuing graded warnings based on the anomaly level of the inspection sub-regions, the efficiency of hazard investigation is improved.

[0111] Regarding the system in the above embodiments, the specific manner in which each module performs its operations has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0112] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0113] Accordingly, this application also provides an electronic device, including: one or more processors; a memory for storing one or more programs; and when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the UAV data processing method for key indicators of oil and gas inspection as described above. Figure 7 The diagram shown is a hardware structure diagram of any device with data processing capabilities, used in an embodiment of the present invention to provide a UAV data processing system for key indicators of oil and gas inspection. (Except for...) Figure 7In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0114] Accordingly, this application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the UAV data processing method for key indicators of oil and gas inspection as described above. The computer-readable storage medium can be an internal storage unit of any data-processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data-processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data-processing device, and can also be used to temporarily store data that has been output or will be output.

[0115] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0116] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for processing UAV data on key indicators of oil and gas inspection, characterized in that, Includes the following steps: Divide the oil and gas inspection sub-regions, collect environmental and equipment status data of the inspection sub-regions in real time, and dynamically adjust the inspection priority of the inspection sub-regions based on the collected data. The current inspection route is dynamically adjusted based on the inspection priority, and multiple drones are coordinated and dispatched to update the inspection status synchronously and upload the inspection data in real time. Specifically: Retrieve the initial routes of each inspection sub-area, dynamically optimize the routes according to the inspection priority, and output the current inspection route adjustment data. Based on the priority of each sub-region and the optimized route, multi-UAV collaborative scheduling is carried out; The system can acquire real-time flight progress, data collection volume, and equipment status of drones during inspection missions, and update the execution status of inspection missions in each sub-area. The system continuously collects environmental and equipment status data from each sub-region, attaching "sub-region identifier + priority label + collection timestamp" to the collected data and uploading it in real time via the WebSocket protocol. If the drone detects an anomaly during inspection, it triggers a priority collection request, extends the hovering time at that location, and collects additional high-definition images and multi-dimensional sensor data, simultaneously marking and uploading the data. In the step of coordinating multi-UAV scheduling based on the priority of each sub-region and the optimized route: Build an initial drone resource pool, establish a real-time updated drone resource pool, and record information on all drones currently available for inspection; Determine the drone requirements for each inspection sub-area, dynamically adjust the flight path parameters and inspection priorities for each inspection sub-area, and calculate the number of drones required for each sub-area, the drone type requirements, and the estimated inspection time. Initial allocation of drone resources: Based on the information from the drone resource pool and the needs of each sub-region, drones are initially allocated from the resource pool to each inspection sub-region. Monitor the supply and demand balance of drone resources, monitor the drone resource usage and task progress in each inspection sub-area in real time, and trigger the resource rescheduling mechanism. Dynamically adjust drone scheduling; for high-priority sub-regions that trigger the resource rescheduling mechanism, select idle drones and send task adjustment instructions to the idle drones. To avoid conflicts and optimize routes, the flight paths of drones were replanned, and their flight altitudes and sequences were adjusted. The flight paths of drones were also optimized in conjunction with the inspection progress of each sub-area. Based on the inspection priority, the inspection data is assigned to a corresponding priority queue for data processing. Combined with key oil and gas indicators, the anomaly level of the inspection sub-area is determined, and graded early warnings are issued.

2. The UAV data processing method for key indicators of oil and gas inspection as described in claim 1, characterized in that, In the process of dividing the oil and gas inspection sub-regions, collecting real-time environmental and equipment status data of the inspection sub-regions, and dynamically adjusting the inspection priority of the inspection sub-regions based on the collected data: Obtain map data of the oil and gas inspection area, divide the overall inspection area into multiple independent inspection sub-areas, and assign a unique identifier code to each sub-area; Set an initial flight path, configure drones for each inspection sub-area, and conduct inspections of each sub-area according to the initial flight path, collecting environmental data and equipment status data in real time. The system presets priority division rules, adjusts the priority of sub-regions based on the collected data, and outputs the adjustment results.

3. The UAV data processing method for key indicators of oil and gas inspection as described in claim 2, characterized in that, After setting the initial flight path, configuring drones for each inspection sub-area, and conducting inspections of each sub-area according to the initial flight path, while collecting environmental and equipment status data in real time: The environmental and equipment status data collected from each sub-region are obtained, and the data is cleaned and preliminarily classified.

4. The UAV data processing method for key indicators of oil and gas inspection as described in claim 2, characterized in that, In the steps of setting a preset priority division rule, adjusting the priority of sub-regions based on the collected data, and outputting the adjustment results: If the priority is adjusted, the task attribute labels of the sub-region will be updated synchronously.

5. The UAV data processing method for key indicators of oil and gas inspection as described in claim 1, characterized in that, After avoiding conflicts and optimizing routes, replanning the flight paths of drones, adjusting flight altitudes and flight sequences, and optimizing drone flight paths in conjunction with the inspection progress of each sub-area: Real-time feedback of scheduling results, recording the entire process of multi-UAV collaborative scheduling, and real-time updates of the task status and inspection sub-area information of each UAV.

6. The UAV data processing method for key indicators of oil and gas inspection as described in claim 1, characterized in that, In the process of allocating corresponding priority queues to inspection data based on inspection priority for data processing, determining the anomaly level of the inspection sub-area in conjunction with key oil and gas indicators, and issuing graded early warnings: Construct a three-level data processing queue corresponding to the inspection priority, and receive inspection data; Differentiated data processing strategies are adopted for different priority queues, and the anomaly level of each inspection sub-area is determined by combining key indicators of oil and gas inspection. Implement tiered early warning systems based on anomaly level and inspection priority.

7. A UAV data processing system for key indicators of oil and gas inspection, applied to the UAV data processing method for key indicators of oil and gas inspection as described in claim 1, characterized in that, This includes a regional inspection priority adjustment module, a task dynamic planning module, and a data processing priority adaptation module; among which: The regional inspection priority adjustment module is used to divide the oil and gas inspection sub-regions, collect environmental and equipment status data of the inspection sub-regions in real time, and dynamically adjust the inspection priority of the inspection sub-regions based on the collected data. The task dynamic planning module is used to dynamically adjust the current inspection route based on inspection priority, coordinate the scheduling of multiple UAVs, synchronously update the inspection status, and upload inspection data in real time; specifically: Retrieve the initial routes of each inspection sub-area, dynamically optimize the routes according to the inspection priority, and output the current inspection route adjustment data. Based on the priority of each sub-region and the optimized route, multi-UAV collaborative scheduling is carried out; The system can acquire real-time flight progress, data collection volume, and equipment status of drones during inspection missions, and update the execution status of inspection missions in each sub-area. The system continuously collects environmental and equipment status data from each sub-region, attaching "sub-region identifier + priority label + collection timestamp" to the collected data and uploading it in real time via the WebSocket protocol. If the drone detects an anomaly during inspection, it triggers a priority collection request, extends the hovering time at that location, and collects additional high-definition images and multi-dimensional sensor data, simultaneously marking and uploading the data. In the step of coordinating multi-UAV scheduling based on the priority of each sub-region and the optimized route: Build an initial drone resource pool, establish a real-time updated drone resource pool, and record information on all drones currently available for inspection; Determine the drone requirements for each inspection sub-area, dynamically adjust the flight path parameters and inspection priorities for each inspection sub-area, and calculate the number of drones required for each sub-area, the drone type requirements, and the estimated inspection time. Initial allocation of drone resources: Based on the information from the drone resource pool and the needs of each sub-region, drones are initially allocated from the resource pool to each inspection sub-region. Monitor the supply and demand balance of drone resources, monitor the drone resource usage and task progress in each inspection sub-area in real time, and trigger the resource rescheduling mechanism. Dynamically adjust drone scheduling; for high-priority sub-regions that trigger the resource rescheduling mechanism, select idle drones and send task adjustment instructions to the idle drones. To avoid conflicts and optimize routes, the flight paths of drones were replanned, and their flight altitudes and sequences were adjusted. The flight paths of drones were also optimized in conjunction with the inspection progress of each sub-area. The data processing priority adaptation module is used to allocate corresponding priority queues to the inspection data according to the inspection priority for data processing, determine the anomaly level of the inspection sub-area in combination with key oil and gas indicators, and issue graded warnings.

Images