Air-ground cooperative unmanned inspection system for oil field station and reservoir and path planning method

Abstract

The invention relates to the technical field of unmanned inspection of oil field stations, and particularly discloses an air-ground cooperative unmanned inspection system for an oil field station and a path planning method, the air-ground cooperative unmanned inspection system comprises an unmanned vehicle and an unmanned aerial vehicle, and the unmanned vehicle is in wireless communication connection with the unmanned aerial vehicle; the unmanned vehicle comprises a take-off and landing charging platform used for bearing an unmanned aerial vehicle and charging the unmanned aerial vehicle; the ground instrument detection module is used for detecting ground instrument parameters; the data acquisition module is used for collecting equipment state data and environment data in an inspection process; the unmanned aerial vehicle comprises an environment monitoring module which is used for monitoring fire-fighting potential safety hazards in a station base area; the high-altitude detection module is used for detecting corrosion, damage and oil leakage conditions of the surface of the oil storage tank; according to the invention, through an air-ground collaborative architecture, all-directional inspection coverage of'ground + high altitude 'of an oil field station is realized, and inspection blind areas of single equipment, especially areas such as the top of an oil storage tank, a tall and large pipeline bracket and the like which are difficult to reach by traditional manual inspection, are effectively eliminated.

Description

Technical Field

[0001] This invention relates to the field of unmanned inspection technology for oilfield stations and depots, specifically to an air-ground collaborative unmanned inspection system and path planning method for oilfield stations and depots. Background Technology

[0002] In the oil and gas industry, oilfield depots are core locations for storing critical energy resources such as crude oil, petroleum products, and liquefied natural gas. They are also crucial nodes ensuring the stable operation of the energy supply chain, and their safety, reliability, and efficiency directly determine the normal operation of the entire oil and gas industry. However, the energy materials stored in oilfield depots are generally flammable and explosive, and the internal equipment systems are vast and complex, encompassing various critical facilities such as storage tanks, pipelines, control valves, and metering instruments. These facilities are prone to corrosion, aging, and leaks during long-term operation. Failure to detect and address these issues promptly can lead to major safety accidents such as fires and explosions, posing a serious threat to the lives of workers and company property. Therefore, regular, comprehensive, and precise inspections of oilfield depots to promptly identify and address potential equipment hazards are critical to ensuring their safe operation.

[0003] With the continuous development of the oil and gas industry, the scale and number of oilfield stations and warehouses are constantly expanding, and traditional manual inspection methods can no longer meet the current inspection needs. Their limitations are mainly reflected in the following three aspects:

[0004] First, the efficiency and accuracy of inspections are insufficient: manual inspections require a significant investment of manpower and resources, and are prone to omissions and misidentifications due to factors such as differences in the subjective judgment of inspectors and their physical fatigue. For example, minor corrosion on the surface of oil storage tanks and small leaks at pipeline interfaces are difficult to identify accurately by manual inspections. At the same time, manual inspections need to proceed step by step along fixed routes, which takes a long time when dealing with the complex equipment layout of large stations and warehouses, making it difficult to achieve efficient coverage.

[0005] Second, there are high personnel safety risks: the working environment of oilfield stations and warehouses is harsh, and some areas contain dangerous factors such as toxic and harmful gases and high-pressure equipment. During manual inspections, staff need to be exposed to high-risk environments, making it difficult to ensure safety. Especially under extreme weather conditions (such as heavy rain, heavy snow, and high temperatures), manual inspections are difficult to carry out normally and are prone to interruption.

[0006] Third, the level of intelligence is low: manual inspection data relies on manual recording by inspectors, and data processing and analysis are lagging behind, making it impossible to achieve real-time early warning and rapid response to hidden dangers; at the same time, manual inspection is difficult to form a standardized inspection process, and the inspection quality is greatly affected by the experience level of personnel, which cannot provide accurate data support for the full life cycle management of station and warehouse equipment.

[0007] To address the pain points of traditional manual inspections, inspection robots, as an automated and intelligent inspection method, are gradually being applied to the field of oilfield station and warehouse inspections. Currently, inspection robots on the market are mainly divided into two categories: ground-based unmanned vehicles and aerial drones. However, single-type inspection robots still have significant shortcomings due to limitations in their kinematic models and functional characteristics.

[0008] Limitations of ground-based unmanned vehicles: Although ground-based unmanned vehicles have strong load capacity and can be equipped with various sensors (such as industrial cameras and lidar) to interact with the environment, and have high stability in autonomous operation, their environmental perception range is limited by the working space. They can only cover the ground and low-lying areas and cannot detect high-altitude areas such as the top of oil storage tanks and tall pipeline supports. At the same time, when faced with complex terrain (such as ditches and steep slopes) in the station and warehouse, some ground-based unmanned vehicles have insufficient obstacle crossing ability and are prone to blind spots in inspection.

[0009] Limitations of aerial drones: Quadcopter drones have the advantages of a wide field of view and fast inspection speed, enabling rapid environmental perception over a large area. They are particularly suitable for scenarios such as high-altitude inspection of oil storage tanks and large-scale fire safety monitoring. However, due to limitations in endurance and payload capacity, drone flight time is usually only 30-60 minutes, and they cannot carry heavy inspection equipment (such as high-precision infrared detectors), making it difficult to complete long-term, high-precision, and complex inspection tasks. In addition, drones are susceptible to electromagnetic interference in complex station and warehouse environments, affecting flight stability and path planning accuracy.

[0010] Path planning technology is the core of autonomous inspection robots, and its performance directly determines the robot's operational efficiency and safety. Currently, path planning algorithms can be categorized by path generation method into graph search methods (such as the A* algorithm), random sampling methods (such as the fast random search tree algorithm), curve interpolation methods (such as the B-spline curve algorithm), and optimal control methods; and by scope into global path planning and local path planning. However, existing path planning technologies still suffer from insufficient adaptability in oilfield station and depot inspection scenarios.

[0011] The shortcomings of unmanned vehicle path planning: Existing path planning algorithms for ground robots (such as traditional ant colony algorithms and A* algorithms) mostly focus on "location reachability" as the core objective, without fully considering the kinematic characteristics of robots with specific chassis. For example, the Ackerman chassis unmanned vehicles commonly used in oilfield station and depot inspections have fixed constraints on their steering angle and curvature. Paths planned by traditional algorithms are prone to problems such as excessively large turning angles and sudden changes in curvature, resulting in bumpy driving or even impassable passage for the unmanned vehicle, affecting the stability and efficiency of the inspection.

[0012] Limitations of UAV path planning: UAV path planning needs to simultaneously meet multiple constraints such as track length, flight altitude, yaw angle, and pitch angle, and must avoid threatening areas such as oil tanks and high-voltage electrical cabinets within the depot. Traditional algorithms such as whale optimization and particle swarm optimization are prone to problems such as low global search efficiency, slow convergence speed, and getting trapped in local optima when dealing with multi-constraint optimization problems. This results in planned tracks that cannot meet the dual requirements of "fast arrival" and "smooth and safe" operation. In particular, in scenarios of continuous inspection of multiple task points within the depot, frequent path adjustments will significantly reduce inspection efficiency.

[0013] In summary, the functional limitations of single inspection robots and the adaptability deficiencies of path planning algorithms in existing oilfield station and depot inspection technologies have become key issues restricting the improvement of inspection efficiency and safety. Therefore, it is urgent to design an air-ground collaborative inspection system and develop a path planning method adapted to this system to achieve complementary advantages between unmanned vehicles and drones, and meet the comprehensive, efficient, and intelligent inspection needs of oilfield stations and depots. Summary of the Invention

[0014] The purpose of this invention is to overcome the limitations of single inspection robots and the poor adaptability of path planning algorithms in the existing technology, and to provide an air-ground collaborative unmanned inspection system and path planning method for oilfield stations and warehouses. Through a master-slave collaborative architecture of unmanned vehicles and drones, combined with an improved path planning algorithm, efficient, comprehensive and safe intelligent inspection of oilfield stations and warehouses can be achieved.

[0015] This invention is implemented as follows:

[0016] According to a first aspect of the present invention, the present invention provides an air-ground coordinated unmanned inspection system for oilfield stations and warehouses, including an unmanned vehicle and an unmanned drone, wherein the unmanned vehicle and the unmanned drone are wirelessly connected.

[0017] The unmanned vehicles include:

[0018] A take-off and landing charging platform, used to carry and charge drones;

[0019] Ground instrument detection module, used to detect ground instrument parameters;

[0020] The data acquisition module is used to collect equipment status data and environmental data during the inspection process;

[0021] The drone includes:

[0022] The environmental monitoring module is used to monitor fire safety hazards in the station and warehouse area;

[0023] The high-altitude detection module is used to detect corrosion, damage, and oil leaks on the surface of oil storage tanks.

[0024] Furthermore, the unmanned vehicle uses an Ackerman chassis, which has obstacle-crossing capabilities and stable operation, and the drone is a quadcopter drone.

[0025] Furthermore, the unmanned vehicle also includes a first battery, a first main control module, a first wireless communication module, and a charging output coil. The ground instrument detection module, data acquisition module, first battery, first wireless communication module, and charging output coil are all electrically connected to the first main control module. The drone also includes a second battery, a second main control module, a second wireless communication module, and a charging input coil. The environmental monitoring module, high-altitude detection module, second battery, second wireless communication module, and charging input coil are all electrically connected to the second main control module. The first wireless communication module and the second wireless communication module are communicatively connected.

[0026] Furthermore, the take-off and landing charging platform has a positioning calibration module, which is electrically connected to the first main control module. When the UAV is about to land on the take-off and landing charging platform, the positioning calibration module obtains the real-time position of the UAV through laser positioning or visual recognition, and transmits the position deviation data to the first main control module. The first main control module sends a calibration command to the second main control module of the UAV through the first wireless communication module, guiding the UAV to land precisely at the position where the charging input coil and the charging output coil are aligned, ensuring efficient charging.

[0027] According to a second aspect of the present invention, the present invention provides an air-ground collaborative unmanned inspection path planning method for oilfield stations and warehouses, used in the aforementioned air-ground collaborative unmanned inspection system for oilfield stations and warehouses, including an unmanned vehicle path planning method and an unmanned aerial vehicle path planning method.

[0028] The autonomous vehicle path planning method includes the following steps:

[0029] S11: A two-dimensional grid mapping method is used to construct a ground environment model of the oilfield station and storage area, and to divide the obstacle area into the passable area;

[0030] S12: Based on the traditional ant colony algorithm, an improved ant colony algorithm is constructed. The distance factor from the candidate node to the target point and the turning angle penalty factor are added to the heuristic function. The path length constraint and path smoothness constraint are incorporated into the objective function, transforming the autonomous vehicle path planning into a multi-objective optimization problem.

[0031] S13: Improve the pheromone update method, including local pheromone update and global pheromone update. Local pheromone update adopts a reward and punishment mechanism, and global pheromone update additionally increases the pheromone concentration of the global optimal path.

[0032] S14: Mathematical analysis of the B-spline curve smoothing algorithm and the curvature constraint of the unmanned vehicle is performed. Based on the path planned by the improved ant colony algorithm, the B-spline curve is used for smoothing to obtain a smooth path that satisfies the kinematic constraints of the unmanned vehicle.

[0033] The UAV path planning method includes the following steps:

[0034] S21: Establish a digital map model of oilfield stations and warehouses to determine inspection task points and threat areas;

[0035] S22: Design a fitness function based on UAV flight constraints and threat zone avoidance requirements;

[0036] S23: Based on the whale optimization algorithm, a chaotic inverse learning strategy, a nonlinear convergence factor, an adaptive weight strategy, a dynamic spiral walk strategy, and a random difference mutation strategy are incorporated to construct a chaotic multi-strategy whale optimization algorithm.

[0037] S24: The fitness function is optimized and solved by the chaotic multi-strategy whale optimization algorithm to obtain the optimal UAV trajectory that satisfies the constraints.

[0038] Furthermore, the UAV flight constraints include track length, flight altitude, yaw angle, and pitch angle.

[0039] Furthermore, in step S12, the steering angle penalty factor is used to penalize paths where the steering angle of the autonomous vehicle is too large, the path length constraint aims to minimize the total path length, and the path smoothness constraint aims to ensure smooth changes in path curvature.

[0040] Furthermore, in step S14, during the B-spline curve smoothing process, the curve control points are adjusted to ensure that the smoothed path meets the maximum curvature constraint of the unmanned vehicle, thereby ensuring the stability of the unmanned vehicle during its movement.

[0041] Furthermore, in step S22, the fitness function comprehensively considers the cost of track length, the cost of threat zone avoidance, and the cost of flight attitude constraints, and its expression is:

[0042] F = α × L + β × T + γ × C;

[0043] Where L is the track length, T is the threat zone penalty value (the greater the intrusion depth, the higher the penalty value when the track intrudes into the threat zone), C is the flight attitude constraint penalty value (a penalty is imposed when the maximum flight altitude, yaw angle or pitch angle is exceeded), and α, β and γ are weighting coefficients and satisfy α + β + γ = 1.

[0044] Furthermore, it also includes air-ground collaborative path coordination steps: the unmanned vehicle sends its own position, ground path and inspection task progress information to the drone in real time through the first wireless communication module; after receiving the information through the second wireless communication module, the drone dynamically adjusts its flight sequence and path in combination with its own planned optimal flight path, so as to ensure that while the unmanned vehicle completes ground instrument testing and equipment status data collection, the drone simultaneously completes fire safety hazard monitoring and high-altitude inspection of oil storage tanks in the corresponding area, thus realizing collaborative inspection between the ground and the air.

[0045] Compared with the prior art, the beneficial effects of the present invention are:

[0046] 1. The air-ground collaborative unmanned inspection system for oilfield stations and warehouses provided by this invention achieves all-round inspection coverage of oilfield stations and warehouses "ground + high altitude" through an air-ground collaborative architecture, effectively eliminating blind spots of single equipment inspection, especially areas that are difficult to reach by traditional manual inspection, such as the top of oil storage tanks and tall pipeline supports.

[0047] 2. This invention provides unmanned vehicles to ensure the continued operation of drones, which greatly extends the effective inspection time of drones and avoids the interruption of inspection tasks due to insufficient drone battery life.

[0048] 3. This invention enables unmanned automated inspection, reducing the risk of workers being exposed to flammable, explosive, toxic, and harmful environments, and significantly improving the safety of inspection operations.

[0049] 4. Through modular design and unified control, the system has good scalability. Sensors or functional modules can be added later according to inspection needs to adapt to more complex scenarios.

[0050] 5. The beneficial effects of the air-ground collaborative unmanned inspection path planning method for oilfield stations and depots provided by this invention are as follows: First, the unmanned vehicle path is adapted to the characteristics of the Ackerman chassis, ensuring driving stability; second, the UAV algorithm optimization improves the efficiency and safety of trajectory planning; third, the collaborative steps ensure that the unmanned vehicle and the UAV are synchronized, improving the overall inspection efficiency and reducing missed inspections. Attached Figure Description

[0051] Figure 1 A block diagram of the electrical control structure of the air-ground coordinated unmanned inspection system for oilfield stations and warehouses provided by the present invention;

[0052] Figure 2 The flowchart of the unmanned vehicle path planning method provided by the present invention is shown below.

[0053] Figure 3 The flowchart of the UAV path planning method provided by the present invention is shown. Detailed Implementation

[0054] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to fixed connections or detachable connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0055] The following description, in conjunction with the accompanying drawings and specific embodiments, provides further details:

[0056] Example 1

[0057] like Figure 1 As shown, this embodiment provides an air-ground collaborative unmanned inspection system for oilfield stations and depots, including unmanned vehicles (UAVs) and drones. Through the complementary functions and collaborative operation of the UAVs and drones, the system solves the problems of incomplete coverage and low efficiency associated with traditional single inspection equipment. The core of this system is the construction of a three-dimensional inspection architecture of "ground mobile platform + high-altitude detection carrier," in which the UAVs and drones achieve real-time data interaction through wireless communication modules, ensuring the synchronous progress of inspection tasks and the unified aggregation of data.

[0058] As the ground core of the system, the unmanned vehicle adopts an Ackerman chassis design. This chassis has excellent obstacle-crossing performance and driving stability, and can easily cope with the complex environment commonly found in oilfield stations and storage facilities, such as gravel roads, gentle slopes, and equipment gaps, providing reliable mobile support for long-term continuous inspections. In terms of functional module configuration, the unmanned vehicle integrates three core functional modules: a take-off and landing charging platform, a ground instrument detection module, and a data acquisition module. The take-off and landing charging platform not only serves as a temporary docking station for drones but also has a built-in charging structure to replenish their power when their flight time is insufficient, effectively addressing the pain point of limited drone cruising time. The ground instrument detection module is equipped with a high-definition industrial camera and infrared sensors, which can automatically identify the parameters of ground instruments such as pressure gauges, flow meters, and thermometers in the station, accurately capturing abnormalities such as pointer deviation, dial damage, and values ​​exceeding the range, avoiding subjective errors from manual inspections. The data acquisition module is responsible for synchronously collecting two types of key data during the inspection process: equipment status data, such as parameter information acquired by the ground instrument detection module and temperature data of equipment surfaces; and environmental data, such as the concentration of combustible gases in the air and ambient temperature and humidity. This data is transmitted in real time to the control center of the unmanned vehicle, providing a basis for subsequent hazard analysis and early warning.

[0059] To ensure the orderly operation of all functional modules, the unmanned vehicle is also equipped with a primary battery, a primary main control module, a primary wireless communication module, and a charging output coil. The primary battery serves as the power source, providing stable power to all the electrical modules of the unmanned vehicle. The primary main control module is the control center of the unmanned vehicle, utilizing an STM32H7 series industrial-grade microcontroller. The ground instrument detection module, data acquisition module, primary battery, primary wireless communication module, and charging output coil are all electrically connected to the primary main control module, enabling unified control, data scheduling, and fault diagnosis of all modules. The primary wireless communication module acts as a data bridge between the unmanned vehicle and the drone, transmitting the unmanned vehicle's location information, inspection progress, and environmental data to the drone in real time, while simultaneously receiving high-altitude detection data from the drone. The charging output coil, in conjunction with the take-off and landing charging platform, provides charging services to the drone through electromagnetic induction, ensuring a safe and efficient charging process.

[0060] Specifically, the take-off and landing charging platform also integrates a positioning calibration module, which is electrically connected to the first main control module and is crucial for achieving precise drone landing. When the drone completes its high-altitude inspection mission and prepares to return to the unmanned vehicle, the positioning calibration module uses laser positioning technology or visual recognition technology (such as a high-definition camera combined with image matching algorithms) to acquire the drone's three-dimensional position coordinates in real time. It then compares these coordinates with the preset landing center point of the take-off and landing charging platform to calculate the position deviation data. This deviation data is immediately transmitted to the first main control module, which generates corresponding calibration commands based on the deviation and sends them to the drone's control unit via the first wireless communication module. This guides the drone to adjust its flight attitude and position, ultimately landing precisely at the point where the charging input coil and charging output coil are aligned. This not only ensures efficient charging but also avoids the risk of equipment collisions due to landing deviations.

[0061] The drone, serving as the system's high-altitude inspection carrier, employs a quadcopter design, featuring vertical takeoff and landing, stable hovering, and flexible steering. It can maneuver flexibly among densely packed equipment such as oil storage tanks and pipeline supports within oilfield stations, covering high-altitude areas inaccessible to unmanned vehicles. The drone's core functional modules include an environmental monitoring module and a high-altitude inspection module. The environmental monitoring module is equipped with an infrared thermal imager and a combustible gas sensor. The infrared thermal imager can quickly scan the station area, capturing abnormally high-temperature points on equipment surfaces and promptly detecting potential fire hazards caused by pipeline leaks or equipment malfunctions. The combustible gas sensor can detect the concentration of combustible gases such as methane and propane in the air in real time, issuing an immediate warning when the concentration exceeds a safe threshold to prevent explosion risks. The high-altitude inspection module is equipped with a high-definition zoom camera, capable of capturing detailed images of the top of oil storage tanks and high sections of the tank walls. Through image recognition algorithms, it accurately identifies defects such as corrosion spots, weld cracks, and oil leaks on the surface of the oil storage tanks, achieving a detection accuracy of up to 0.1 mm, effectively compensating for blind spots in ground inspections.

[0062] Corresponding to the unmanned vehicle, the drone is also equipped with a second battery, a second main control module, a second wireless communication module, and a charging input coil. The second battery powers the drone's flight mechanism and detection modules. When the battery level drops below 20%, it automatically triggers a return-to-home command, returning to the unmanned vehicle's takeoff and landing charging platform to replenish its power. The second main control module serves as the drone's control center. The environmental monitoring module, high-altitude detection module, second battery, second wireless communication module, and charging input coil are all electrically connected to the second main control module, enabling flight control, detection task scheduling, and data processing. The second wireless communication module maintains bidirectional communication with the unmanned vehicle's first wireless communication module, ensuring real-time synchronization of information between the two and providing data support for air-to-ground collaborative inspections. The charging input coil is matched with the unmanned vehicle's charging output coil, receiving electrical energy through electromagnetic induction to achieve stable charging.

[0063] The air-ground collaborative unmanned inspection system for oilfield stations and storage facilities provided by this invention achieves comprehensive "ground + high-altitude" inspection coverage through an air-ground collaborative architecture, effectively eliminating blind spots for single-equipment inspections, especially in areas difficult to reach by traditional manual inspections, such as the tops of oil storage tanks and tall pipeline supports. This invention provides unmanned vehicles with extended battery life for drones, significantly extending the effective inspection time of drones and preventing inspection interruptions due to insufficient drone battery life. This invention enables unmanned automated inspections, reducing the risk of personnel exposure to flammable, explosive, toxic, and hazardous environments, and significantly improving the safety of inspection operations. Furthermore, through modular design and unified control, the system has excellent scalability; sensors or functional modules can be added later to adapt to more complex scenarios based on inspection needs.

[0064] Example 2

[0065] This embodiment provides a method for unmanned inspection path planning of oilfield stations and warehouses using air-ground collaboration. It is specifically designed for the air-ground collaborative unmanned inspection system of oilfield stations and warehouses provided in Embodiment 1. The aim is to ensure that unmanned vehicles and drones can complete inspection tasks efficiently and safely in complex station and warehouse environments through scientific path optimization and collaborative scheduling. The method mainly includes three parts: unmanned vehicle path planning, drone path planning, and air-ground collaborative path coordination. Each part is specifically designed for equipment characteristics and inspection requirements.

[0066] like Figure 2 As shown, the autonomous vehicle path planning, with the core objective of "adapting to the motion characteristics of the Ackerman chassis and ensuring a smooth and passable path," is implemented in four steps:

[0067] S11: A two-dimensional grid mapping method is used to construct a ground environment model of the oilfield station and storage facility, dividing the area into obstacle areas and passable areas. Based on the layout of the oilfield station and storage facility, a two-dimensional grid mapping method is used to construct the ground environment model, dividing the station and storage facility into grids of fixed size. Obstacle areas (such as oil tank bases and walls), passable areas (such as inspection passages), and task areas (such as the location of ground instruments) are marked, providing clear environmental boundaries for path planning.

[0068] S12: Based on the traditional ant colony algorithm, an improved ant colony algorithm is constructed. Specifically, a distance factor from the candidate node to the target point and a steering angle penalty factor are added to the heuristic function. The distance factor guides the algorithm to search accurately towards the target point, and the steering angle penalty factor avoids planning paths that exceed the steering capabilities of the Ackerman chassis. At the same time, path length constraints (aiming at minimizing the total path length) and path smoothness constraints (aiming at ensuring smooth changes in path curvature) are incorporated into the objective function, transforming autonomous vehicle path planning into a multi-objective optimization problem.

[0069] S13: Improve the pheromone update method by adopting a two-level pheromone update of "local + global": Local update uses a reward and punishment mechanism to increase the pheromone concentration for short and smooth high-quality paths and decrease the concentration for poor-quality paths to speed up convergence; Global update adds an extra pheromone concentration to the global optimal path to strengthen the guidance of the optimal path and avoid the algorithm from getting stuck in local optima.

[0070] S14: Mathematical analysis of the B-spline curve smoothing algorithm and the curvature constraint of the unmanned vehicle is performed. Based on the path planned by the improved ant colony algorithm, the B-spline curve is used for smoothing to obtain a smooth path that meets the kinematic constraints of the unmanned vehicle. The smoothed path meets the maximum curvature requirement of the Ackerman chassis, ensuring that the unmanned vehicle drives smoothly without sharp turns or bumps.

[0071] like Figure 3 As shown, the UAV path planning method aims for "rapid arrival and safe obstacle avoidance" and is implemented in four steps:

[0072] S21: Establish a digital map model of oilfield stations and storage facilities to identify inspection task points such as the top detection point of the oil storage tank and threat areas such as high-voltage electrical cabinets and no-fly zones.

[0073] S22: Design a fitness function based on UAV flight constraints and threat zone avoidance requirements. UAV flight constraints include track length, flight altitude, yaw angle, and pitch angle. The fitness function comprehensively considers track length cost, threat zone avoidance cost, and flight attitude constraint cost, and its expression is:

[0074] F = α × L + β × T + γ × C;

[0075] Where L is the track length, T is the threat zone penalty value (the greater the intrusion depth, the higher the penalty value when the track intrudes into the threat zone), C is the flight attitude constraint penalty value (a penalty is imposed when the maximum flight altitude, yaw angle or pitch angle is exceeded), and α, β and γ are weighting coefficients and satisfy α + β + γ = 1.

[0076] S23: Based on the whale optimization algorithm, a chaotic multi-strategy whale optimization algorithm is constructed by incorporating a chaotic reverse learning strategy (to improve the diversity of the initial population), a nonlinear convergence factor (to balance global and local search), an adaptive weight strategy (to dynamically adjust the search focus), a dynamic spiral walk strategy, and a random difference mutation strategy (to avoid local optima).

[0077] S24: The fitness function is optimized and solved by the chaotic multi-strategy whale optimization algorithm to obtain the optimal UAV trajectory that satisfies the constraints.

[0078] In addition, the air-ground collaborative path coordination steps include: the unmanned vehicle sends its own position, ground path and inspection task progress information to the drone in real time through the first wireless communication module; after receiving the information through the second wireless communication module, the drone dynamically adjusts its flight sequence and path in combination with its own planned optimal flight path, so as to ensure that when the unmanned vehicle completes the ground instrument detection and equipment status data collection, the drone simultaneously completes the fire safety hazard monitoring of the corresponding area and the high-altitude detection of the oil storage tank, thus realizing the collaborative inspection of the ground and the air.

[0079] The beneficial effects of the air-ground collaborative unmanned inspection path planning method for oilfield stations and depots provided in this embodiment are as follows: First, the unmanned vehicle path is adapted to the characteristics of the Ackerman chassis, ensuring driving stability; second, the optimization of the UAV algorithm improves the efficiency and safety of trajectory planning; and third, the collaborative steps ensure that the unmanned vehicle and the UAV are synchronized, improving the overall inspection efficiency and reducing missed inspections.

[0080] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An unmanned inspection system for oilfield stations and depots that combines air and ground operations, characterized in that: This includes unmanned vehicles and drones, which are wirelessly connected. The unmanned vehicles include: A take-off and landing charging platform, used to carry and charge drones; Ground instrument detection module, used to detect ground instrument parameters; The data acquisition module is used to collect equipment status data and environmental data during the inspection process; The drone includes: The environmental monitoring module is used to monitor fire safety hazards in the station and warehouse area; The high-altitude detection module is used to detect corrosion, damage, and oil leaks on the surface of oil storage tanks.

2. The air-ground coordinated unmanned inspection system for oilfield stations and depots according to claim 1, characterized in that, The unmanned vehicle uses an Ackerman chassis and has obstacle-crossing capabilities and stable operation. The drone is a quadcopter.

3. The air-ground coordinated unmanned inspection system for oilfield stations and depots according to claim 1, characterized in that, The unmanned vehicle further includes a first battery, a first main control module, a first wireless communication module, and a charging output coil. The ground instrument detection module, data acquisition module, first battery, first wireless communication module, and charging output coil are all electrically connected to the first main control module. The drone further includes a second battery, a second main control module, a second wireless communication module, and a charging input coil. The environmental monitoring module, high-altitude detection module, second battery, second wireless communication module, and charging input coil are all electrically connected to the second main control module. The first wireless communication module and the second wireless communication module are communicatively connected.

4. The air-ground coordinated unmanned inspection system for oilfield stations and depots according to claim 3, characterized in that, The take-off and landing charging platform has a positioning calibration module, which is electrically connected to the first main control module. When the UAV is about to land on the take-off and landing charging platform, the positioning calibration module obtains the real-time position of the UAV through laser positioning or visual recognition, and transmits the position deviation data to the first main control module. The first main control module sends a calibration command to the second main control module of the UAV through the first wireless communication module, guiding the UAV to land precisely at the position where the charging input coil and the charging output coil are aligned.

5. A method for unmanned inspection path planning of oilfield stations and depots using air-ground coordination, used in the unmanned inspection system of oilfield stations and depots using air-ground coordination as described in any one of claims 1-4, characterized in that, This includes path planning methods for autonomous vehicles and path planning methods for unmanned aerial vehicles; The autonomous vehicle path planning method includes the following steps: S11: A two-dimensional grid mapping method is used to construct a ground environment model of the oilfield station and storage area, and to divide the obstacle area into the passable area; S12: Based on the traditional ant colony algorithm, an improved ant colony algorithm is constructed. The distance factor from the candidate node to the target point and the turning angle penalty factor are added to the heuristic function, and the path length constraint and path smoothness constraint are incorporated into the objective function. S13: Improve the pheromone update method, including local pheromone update and global pheromone update. Local pheromone update adopts a reward and punishment mechanism, and global pheromone update additionally increases the pheromone concentration of the global optimal path. S14: Mathematical analysis of the B-spline curve smoothing algorithm and the curvature constraint of the unmanned vehicle is performed. Based on the path planned by the improved ant colony algorithm, the B-spline curve is used for smoothing to obtain a smooth path that satisfies the kinematic constraints of the unmanned vehicle. The UAV path planning method includes the following steps: S21: Establish a digital map model of oilfield stations and warehouses to determine inspection task points and threat areas; S22: Design a fitness function based on UAV flight constraints and threat zone avoidance requirements; S23: Based on the whale optimization algorithm, a chaotic inverse learning strategy, a nonlinear convergence factor, an adaptive weight strategy, a dynamic spiral walk strategy, and a random difference mutation strategy are incorporated to construct a chaotic multi-strategy whale optimization algorithm. S24: The fitness function is optimized and solved by the chaotic multi-strategy whale optimization algorithm to obtain the optimal UAV trajectory that satisfies the constraints.

6. The intelligent hoisting method for a long-span cable-stayed crane system according to claim 5, characterized in that, The flight constraints of the UAV include track length, flight altitude, yaw angle, and pitch angle.

7. The intelligent hoisting method for a long-span cable-stayed crane system according to claim 5, characterized in that, In step S12, the steering angle penalty factor is used to penalize paths where the steering angle of the autonomous vehicle is too large, the path length constraint aims to minimize the total path length, and the path smoothness constraint aims to ensure that the path curvature changes smoothly.

8. The intelligent hoisting method for a long-span cable-stayed crane system according to claim 5, characterized in that, In step S14, during the B-spline curve smoothing process, the curve control points are adjusted to ensure that the smoothed path meets the maximum curvature constraint of the unmanned vehicle, thereby ensuring the stability of the unmanned vehicle during its movement.

9. The intelligent hoisting method for a long-span cable-stayed crane system according to claim 5, characterized in that, In step S22, the fitness function comprehensively considers the cost of track length, the cost of threat zone avoidance, and the cost of flight attitude constraints, and its expression is: F = α × L + β × T + γ × C; Where L is the track length, T is the threat zone penalty value, C is the flight attitude constraint penalty value, and α, β, γ are weight coefficients that satisfy α + β + γ = 1.

10. The intelligent hoisting method for a long-span cable-stayed crane system according to claim 5, characterized in that, It also includes air-ground collaborative path coordination steps: the unmanned vehicle sends its own position, ground path and inspection task progress information to the drone in real time; after receiving the information, the drone dynamically adjusts its flight sequence and path based on its own planned optimal flight path, so as to ensure that while the unmanned vehicle completes ground instrument testing and equipment status data collection, the drone simultaneously completes fire safety hazard monitoring and high-altitude inspection of oil storage tanks in the corresponding area, thus realizing collaborative inspection between the ground and the air.

Images