Reservoir inspection method and reservoir inspection system based on AR
By attaching circular magnetic sheets to the reservoir ground and equipment surface and using the AR system to generate AR real scenes, the problem that drones or robots cannot obtain long-distance vision in special weather is solved, and reservoir inspection and equipment renovation are realized in harsh environments.
Patent Information
- Application Number
- CN202510204286.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-24
- Publication Date
- 2025-05-27
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In special weather environments, the cameras of drones or robots in the existing reservoir inspection system cannot obtain a long-range view, resulting in the inability to remotely conduct reservoir inspections and equipment renovations. The existing technology lacks effective solutions.
AR-based reservoir inspection methods and systems are adopted, and the drone attaches circular magnetic sheets to the reservoir ground and equipment surfaces to establish a magnetic sheet coordinate system. The AR system combines the real-life data of the reservoir captured by the drone with the magnetic sheet coordinate system data to generate AR real-life scenes, and then controls the maintenance robot or unmanned ship to move in the AR real-life scene and conducts patrol and simple inspection.
In severe weather, drones or robots can conduct normal inspections and simple inspections without directly obtaining long-distance vision, which reduces the work intensity of engineers and improves the stability and reliability of reservoir inspection work.
Smart Images
Figure CN120050395A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of reservoir inspection, and particularly to an AR-based reservoir inspection method and a reservoir inspection system. Background Art
[0002] As an important water conservancy facility, the reservoir dam needs to be inspected regularly to ensure the normal operation of the reservoir dam facilities. There are also some small devices installed on the reservoir dam. The existing inspection system uses drones to explore the terrain or uses cameras to capture images of the reservoir and reservoir equipment, and transmits the images and data back to the main control console to achieve the effect of remote observation.
[0003] However, the existing inspection system has the following problems: The inspection method of the existing inspection system is to convert the drone footage into AR data in real time, and then transmit the AR data to the console. Engineers obtain the AR footage of the reservoir inspection through the console. For example, the reservoir environment information and the status of reservoir equipment are formed in the field of view of the drone, enabling engineers to conduct inspections around the reservoir. However, the existing inspection method is not applicable to special weather conditions. For example, in rainy days or windy days, the drone cannot take off normally for real-time inspection work, and it is impossible to detect faults in reservoir equipment in a timely manner. Due to the presence of fog and other conditions in the air on rainy and windy days, blocking the field of view, the cameras of existing drone robots cannot obtain a far field of view for movement and equipment repair. Therefore, engineers still need to travel to the reservoir for equipment maintenance, resulting in a very difficult inspection and repair process.
[0004] Regarding the problem that in special weather conditions, the cameras of drones or robots in the existing inspection methods cannot obtain a far field of view for movement and equipment repair, resulting in the inability to remotely conduct reservoir inspections and equipment repairs, no effective solution has been proposed yet. Summary of the Invention
[0005] In the present invention, an AR-based reservoir inspection method and a reservoir inspection system are provided to solve the problem that in special weather conditions, the cameras of drones or robots in the existing inspection methods cannot obtain a far field of view for movement and equipment repair, resulting in the inability to remotely conduct reservoir inspections and equipment repairs.
[0006] In the first aspect, an AR-based reservoir inspection method is provided in the present invention, which is applied to a reservoir inspection system. The reservoir inspection system includes several circular magnetic sheets, a drone, an AR system, a maintenance robot, and a main control console. The drone has a multi-angle photography function and a patch mechanism is installed at the bottom. The AR system is used to receive the images captured by the drone and convert them into AR images. The maintenance robot is communicatively connected to the AR system and has a multi-angle camera function. The main control console is used to display the AR real scenes in the fields of view of the drone and the maintenance robot.
[0007] The AR-based reservoir inspection method is executed by a total control console and includes:
[0008] Controlling the movement of the inspection robot. When the inspection robot's vision captures the current circular magnetic sheet, determining the position of the inspection robot in the AR real scene based on the current circular magnetic sheet, and controlling the inspection robot to move to the target position based on the positions of the inspection robot and the target position in the AR real scene;
[0009] The steps for establishing the AR real scene include:
[0010] Controlling the drone to travel along the inspection route, take pictures to obtain the reservoir real scene, and regularly arrange and attach a number of circular magnetic sheets on the roadside and the surfaces of reservoir equipment along the way; establishing a magnetic sheet coordinate system based on the arrangement positions of the number of circular magnetic sheets, and transmitting the reservoir real scene data and the magnetic sheet coordinate system data captured by the drone to the AR system to establish the AR real scene.
[0011] Furthermore, controlling the drone to travel along the inspection route, take pictures to obtain the reservoir real scene, and regularly arrange and attach a number of circular magnetic sheets on the roadside and the surfaces of reservoir equipment along the way includes: controlling the drone to travel along the inspection route of the inspection robot, taking pictures of the real scene around the inspection route during the travel, and successively attaching circular magnetic sheets along the inspection route of the inspection robot. Some of the inspection routes extend to the reservoir equipment, and controlling the drone to successively attach circular magnetic sheets on the reservoir equipment.
[0012] Furthermore, establishing a magnetic sheet coordinate system based on the arrangement positions of the number of circular magnetic sheets, and transmitting the reservoir real scene data and the magnetic sheet coordinate system data captured by the drone to the AR system to establish the AR real scene includes: digitalizing the distance difference and height difference between the circular magnetic sheets, establishing a magnetic sheet coordinate system with the first circular magnetic sheet as the coordinate origin, digitalizing the reservoir real scene data and transforming it into AR real scene data through 3D modeling, and corresponding and combining the AR real scene data with the magnetic sheet coordinate system to generate an AR real scene with coordinate basis.
[0013] Furthermore, determining the position of the inspection robot in the AR real scene based on the current circular magnetic sheet, and controlling the inspection robot to move to the target position based on the positions of the inspection robot and the target position in the AR real scene includes: the AR real scene displays the entire reservoir panorama. When the inspection robot recognizes the circular magnetic sheet on the ground, obtains the coordinates of the inspection robot in the magnetic sheet coordinate system, and formulates a movement instruction for the inspection robot according to the coordinates of the inspection robot and the coordinates of the target position. When the inspection robot moves to the target position, the inspection robot obtains an updated local AR real scene of the equipment by closely recognizing the circular magnetic sheet of the reservoir equipment, and performs simple inspection operations on the reservoir equipment based on the AR real scene.
[0014] Further, based on the current circular magnetic sheet, determine the position of the inspection robot in the AR real scene. Based on the positions of the inspection robot and the target position in the AR real scene, control the inspection robot to move to the target position, including: when the inspection robot recognizes the circular magnetic sheet on the ground and obtains the coordinates of the inspection robot in the magnetic sheet coordinate system, at this time, the AR system generates a pre-modeled AR real scene within the field of view of the inspection robot according to the coordinates of the inspection robot. Then, control the inspection robot to move to the target position with reference to the AR real scene. When the inspection robot moves to the target position, the inspection robot obtains an updated local AR real scene of the equipment by closely recognizing the circular magnetic sheet of the reservoir equipment, and performs simple inspection operations on the reservoir equipment based on the AR real scene.
[0015] Further, the reservoir inspection system further includes an unmanned boat, which is communicatively connected to the AR system and has a multi-angle camera function; the AR-based reservoir inspection method further includes: the master console controls the movement of the unmanned boat. When the current circular magnetic sheet is captured in the field of view of the unmanned boat, determine the position of the unmanned boat in the AR real scene based on the current circular magnetic sheet, and control the unmanned boat to move to the target position based on the positions of the unmanned boat and the target position in the AR real scene.
[0016] In a second aspect, the present invention provides a reservoir inspection system, including: a drone, an AR system, an inspection robot, and a master console. The drone has a multi-angle photography function and a patch mechanism is installed at the bottom. The patch mechanism includes a hollow cylindrical tube and a linear reciprocating mechanism. The hollow cylindrical tube is provided with a side straight groove, and several circular magnetic sheets are arranged and placed inside the hollow cylindrical tube. The linear reciprocating mechanism is installed on the outer wall of the hollow cylindrical tube and is used to sequentially push the circular magnetic sheets out of the hollow cylindrical tube through the side straight groove. The hollow cylindrical tube is installed at the bottom of the drone. The AR system is used to receive the images captured by the drone and convert them into AR images. The inspection robot is communicatively connected to the AR system and has a multi-angle camera function. The master console is used to display the AR real scenes in the fields of view of the drone and the inspection robot.
[0017] Further, it further includes an unmanned boat, and an omnidirectional camera is installed on the unmanned boat, and the omnidirectional camera is communicatively connected to the AR system and the master console.
[0018] Further, an omnidirectional camera is installed on the inspection robot, and the omnidirectional camera is communicatively connected to the AR system and the master console.
[0019] Further, the linear reciprocating mechanism includes a linear motor, an electromagnet, and a card. The linear motor is fixedly installed on the outer wall of the hollow cylindrical tube, the electromagnet is fixed at the end of the moving end of the linear motor and faces the side straight groove of the hollow cylindrical tube, and the card is fixed at the bottom end of the side straight groove of the hollow cylindrical tube and is used to separate the circular magnetic sheet from the electromagnet.
[0020] Compared with the related technologies, the present invention has the following beneficial effects:
[0021] 1. It is not necessary to obtain the long-distance view of the actual scene. Only by pre-collecting data and performing three-dimensional modeling on the actual scene in advance, the virtual real scene can be completely displayed in the field of view of the inspection robot or unmanned ship through the AR system. Thus, even if the inspection robot or unmanned ship cannot see the appearance of the reservoir in the actual scene, it can still perform normal inspection and simple maintenance operations based on the magnetic sheet coordinate system and the virtual field of view of the AR real scene, which is beneficial to reducing the work intensity of engineers and is applicable to inspection and maintenance operations in bad weather, improving the stability of the daily reservoir inspection work and ensuring the normal execution of the reservoir inspection work.
[0022] 2. An omnidirectional camera is installed on the inspection robot and is communicatively connected to the AR system. An omnidirectional camera is installed on the unmanned ship, and the omnidirectional camera of the unmanned ship is communicatively connected to the AR system and the total console. The total console is used to display the AR real scene in the fields of view of the unmanned aerial vehicle and the inspection robot, facilitating engineers to observe and control.
[0023] 3. During actual use, the movement instruction of the inspection robot can be formulated according to the coordinates of the inspection robot and the coordinates of the target position. When the inspection robot moves to the target position, simple maintenance operations can be performed on the reservoir equipment based on the AR real scene. It is also possible to generate the pre-modeled AR real scene within the field of view of the inspection robot according to the coordinates of the inspection robot. At this time, control the inspection robot to move to the target position with reference to the AR real scene and perform simple maintenance operations on the reservoir equipment based on the AR real scene. Engineers can choose one of the above two methods for operation according to requirements and actual situations to facilitate faster and more convenient inspection operations.
[0024] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more concise and understandable. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] Figure 1 is a perspective view of the patch mechanism in the embodiment;
[0026] Figure 2 is a flowchart of the AR-based reservoir inspection method in the embodiment;
[0027] Figure 3 is a flowchart of the steps for establishing the AR real scene in the embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0028] To understand the purpose, technical solution, and advantages of the present application more clearly, the present application will be described and illustrated below with reference to the drawings and embodiments.
[0029] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meanings understood by those with ordinary skills in the technical field to which this application belongs. In this application, words such as "a", "an", "one kind", "the", "these" and the like do not indicate a limitation in quantity, and they can be singular or plural. The terms "including", "containing", "having" and any variants thereof involved in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or device containing a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent in these processes, methods, products or devices. The words such as "connected", "linked", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application means two or more than two. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, and B exists alone. Usually, the character " / " means that the objects associated before and after are in an "or" relationship. The terms "first", "second", "third" and the like involved in this application only distinguish similar objects and do not represent a specific order for the objects.
[0030] In an embodiment, an AR-based reservoir inspection method and a reservoir inspection system are provided, which are used to solve the problem in the prior art that the cameras of drones or robots cannot obtain a far field of view for movement and equipment renovation in special weather environments, resulting in the inability to remotely conduct reservoir inspection and equipment renovation. To solve the above problems, this embodiment provides an AR-based reservoir inspection method and a corresponding reservoir inspection system.
[0031] First, this embodiment introduces a reservoir inspection system, which includes: a number of circular magnetic sheets 12, a drone, an AR system, a maintenance robot, an unmanned boat and a general console. The main function of the drone is to pre-scan the terrain and equipment information of the reservoir and store it. The AR system is the augmented reality technology and its system used in the prior art. By importing the pre-scanned terrain and equipment information of the reservoir into the AR system, the AR system can perform three-dimensional modeling based on the terrain and equipment information to convert the terrain and equipment information into an AR real scene. The general console includes an AR display device, a control device for the maintenance robot and a control device for the unmanned boat, and can remotely obtain the omnidirectional camera views of the maintenance robot and the unmanned boat, as well as the omnidirectional camera views combined with the AR real scene.
[0032] Among them, the drone has a multi-angle photography function and a patch mechanism 1 is installed at the bottom. An omnidirectional camera is installed on the drone to achieve the multi-angle photography function. Please refer to Figure 1 , the patch mechanism 1 includes a hollow cylindrical tube 11 and a linear reciprocating mechanism 13. The top disc area of the hollow cylindrical tube 11 is used for installation at the bottom of the drone. At the same time, to ensure the flight stability of the drone and the patch work efficiency, a set of hollow cylindrical tubes 11 can be set and symmetrically installed on the bottom side of the drone. The hollow cylindrical tube 11 is provided with a side straight groove. A number of circular magnetic sheets 12 are arranged and placed inside the hollow cylindrical tube 11. The linear reciprocating mechanism 13 is installed on the outer wall of the hollow cylindrical tube 11 and is used to sequentially push the circular magnetic sheets 12 out of the hollow cylindrical tube 11 through the side straight groove. The hollow cylindrical tube 11 is installed at the bottom of the drone. The linear reciprocating mechanism 13 includes a linear motor 131, an electromagnet 132, and a card 133. The linear motor 131 is fixedly installed on the outer wall of the hollow cylindrical tube 11. The electromagnet 132 is fixed at the end of the moving end of the linear motor 131 and faces the side straight groove of the hollow cylindrical tube 11. The card 133 is fixed at the bottom end of the side straight groove of the hollow cylindrical tube 11 and is used to separate the circular magnetic sheet 12 from the electromagnet 132. To improve the separation effect of the card 133 on the circular magnetic sheet 12 and the electromagnet 132, the cross-section of the card 133 can be set as a triangle, and the top of the triangle is used to separate the circular magnetic sheet 12 and the electromagnet 132 faster. The power supplies of the electromagnet 132 and the linear motor 131 are provided by the drone power supply. The circular magnetic sheet 12 is retained by the friction force with the inner wall of the hollow cylindrical tube 11. Therefore, without external force, the circular magnetic sheet 12 will not fall naturally. When attaching the circular magnetic sheet 12, the linear motor 131 is driven to drive the electromagnet 132 at the end of the linear motor 131 to move. When the electromagnet 132 retracts to the first position, the side of the circular magnetic sheet 12 at the first position is adsorbed together with the electromagnet 132 by magnetic force. Subsequently, the linear motor 131 is driven to drive the electromagnet 132 at the end of the linear motor 131 to move, so that the circular magnetic sheet 12 at the first position extends until the bottom end of the side straight groove of the hollow cylindrical tube 11. At this time, the tip of the card 133 passes through the middle of the circular magnetic sheet 12 and the electromagnet 132 to separate the circular magnetic sheet 12 from the electromagnet 132. Subsequently, the circular magnetic sheet 12 at the first position is attached to the reservoir ground or reservoir equipment or reservoir water bank. And so on, all subsequent circular magnetic sheets 12 are attached at the set positions, thus forming the magnetic sheet coordinate system of the circular magnetic sheets 12.
[0033] In addition, the AR system is used to receive the images captured by the drone and convert them into AR images. An omnidirectional camera is installed on the inspection robot and is communicatively connected to the AR system. An omnidirectional camera is installed on the unmanned boat, and the omnidirectional camera of the unmanned boat is communicatively connected to the AR system and the master console. The master console is used to display the AR live scenes in the fields of view of the drone and the inspection robot, facilitating the engineers to observe and control. Secondly, this embodiment also introduces an AR-based reservoir inspection method applied to the above-mentioned reservoir inspection system. Please refer to Figure 2 , and this AR-based reservoir inspection method is executed by the master console and includes: steps S100, S200, and S300.
[0034] S100, control the movement of the inspection robot.
[0035] This step can be understood as that the master console starts the inspection robot or the unmanned boat, and controls the inspection robot or the unmanned boat to move and explore the circular magnetic sheet 12.
[0036] S200, when the field of view of the inspection robot or the unmanned boat captures the current circular magnetic sheet 12, determine the position of the inspection robot or the unmanned boat in the AR live scene based on the current circular magnetic sheet 12.
[0037] This step can be understood as that when the inspection robot is controlled to explore the circular magnetic sheet 12, it is known which position in the magnetic sheet coordinate system the inspection robot or the unmanned boat is located. Since the magnetic sheet coordinate system and the AR live scene are in a corresponding relationship, that is, according to the magnetic sheet coordinate system, the actual distances between various objects in the AR live scene can be known, so that the position of the inspection robot or the unmanned boat in the AR live scene can be determined.
[0038] S300, based on the position of the inspection robot and the target position in the AR live scene, control the inspection robot to move to the target position.
[0039] Step S300 can be divided into different operations in two cases. In this embodiment, this step may include: the AR live scene displays the panoramic view of the reservoir. When the inspection robot recognizes the circular magnetic sheet 12 on the ground, the coordinates of the inspection robot in the magnetic sheet coordinate system are obtained, and a movement instruction for the inspection robot is formulated based on the coordinates of the inspection robot and the coordinates of the target position. When the inspection robot moves to the target position, the inspection robot obtains the updated local AR live scene of the equipment by closely recognizing the circular magnetic sheet 12 of the reservoir equipment, and performs simple inspection operations on the reservoir equipment according to the AR live scene.
[0040] In some other embodiments, this step may further include: when the inspection robot recognizes the circular magnetic tiles 12 on the ground, obtaining the coordinates of the inspection robot in the magnetic tile coordinate system. At this time, the AR system generates a pre-modeled AR real scene within the field of view of the inspection robot according to the coordinates of the inspection robot. Then, control the inspection robot to move to the target position with reference to the AR real scene. When the inspection robot moves to the target position, the inspection robot obtains an updated local AR real scene of the equipment by closely recognizing the circular magnetic tiles 12 of the reservoir equipment, and performs simple inspection operations on the reservoir equipment based on the AR real scene.
[0041] When actually using this step, the movement instruction of the inspection robot can be formulated according to the coordinates of the inspection robot and the coordinates of the target position. When the inspection robot moves to the target position, simple inspection operations are performed on the reservoir equipment based on the AR real scene. It can also generate a pre-modeled AR real scene within the field of view of the inspection robot according to the coordinates of the inspection robot. Then, control the inspection robot to move to the target position with reference to the AR real scene and perform simple inspection operations on the reservoir equipment based on the AR real scene. Engineers can choose one of the above two methods according to requirements and actual situations to facilitate faster and more convenient inspection operations.
[0042] Please refer to Figure 3 , the establishment steps of the AR real scene include: steps S400, S410, and S420.
[0043] S400, control the drone to travel along the inspection route, take pictures to obtain the real scene of the reservoir, and attach a number of circular magnetic tiles 12 regularly on the surface of the road along the way and the reservoir equipment through the pasting mechanism 1.
[0044] This step can be understood as controlling the drone to travel along the inspection route of the inspection robot or the unmanned ship. During the travel, take pictures of the real scene around the inspection route, and attach circular magnetic tiles 12 in sequence along the inspection route of the inspection robot or the unmanned ship. Some of the inspection routes extend to the reservoir equipment, and control the drone to attach circular magnetic tiles 12 on the reservoir equipment in sequence. The inspection route refers to all the routes that the inspection robot or the unmanned ship needs to pass through when performing the inspection task. The purpose of this step is to attach a number of circular magnetic tiles 12 at different positions of the reservoir to establish a magnetic tile coordinate system.
[0045] S410, establish a magnetic tile coordinate system based on the arrangement positions of a number of circular magnetic tiles.
[0046] This step can be understood as comparing a number of circular magnetic tiles 12 to each coordinate point in the coordinate system. After determining the arrangement positions of a number of circular magnetic tiles 12, a coordinate system for quantifying the real distance can be established according to the ratio of the actual distance to the simulated distance.
[0047] S420, transmit the actual reservoir scene data and magnetic sheet coordinate system data captured by the drone to the AR system to establish an AR real scene.
[0048] This step can be understood as digitizing the distance difference and height difference data between the circular magnetic sheets 12, establishing a magnetic sheet coordinate system with the initial circular magnetic sheet 12 as the coordinate origin, digitizing the reservoir actual scene data and transforming it into AR real scene data through 3D modeling, and corresponding and combining the AR real scene data with the magnetic sheet coordinate system to generate an AR real scene with coordinate basis. For example, an initial coordinate point is set up in advance, the reservoir actual scene data is digitized into multiple 3D coordinate points, and by measuring the distance difference and height difference between the initial coordinate point and the multiple 3D coordinate points, a virtual model of the reservoir actual scene is established, and the size data of this virtual model is consistent with the real reservoir actual scene, so as to achieve the effect of accurately guiding the inspection robot and unmanned boat through the AR real scene. The advantage of this method is that there is no need to obtain the long-distance view of the actual scene. Only by pre-collecting the data of the actual scene and performing 3D modeling in advance, the virtual real scene can be completely displayed in the field of view of the inspection robot or unmanned boat through the AR system. Thus, even when the inspection robot or unmanned boat cannot see the appearance of the reservoir in the actual scene, it can still perform normal inspection and simple maintenance operations based on the magnetic sheet coordinate system and the virtual field of view of the AR real scene, which is beneficial to reducing the work intensity of engineers and is applicable to inspection and maintenance operations in bad weather, improving the stability of the daily reservoir inspection work and ensuring the normal execution of the reservoir inspection work.
[0049] It should be understood that the specific embodiments described herein are only used to explain this application, rather than to limit it. According to the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present application.
[0050] Obviously, the accompanying drawings are only some examples or embodiments of the present application. For those of ordinary skill in the art, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it can be understood that although the work done during this development process may be complex and time-consuming, for those of ordinary skill in the art, some design, manufacturing or production changes made based on the technical content disclosed in the present application are only conventional technical means and should not be regarded as insufficient disclosure of the present application.
Claims
1. A reservoir inspection method based on AR, applied to a reservoir inspection system, characterized in that: The reservoir inspection system includes: A plurality of circular magnetic sheets (12); A drone having a multi-angle photography function and a patch mechanism (1) installed on the bottom; An AR system, which is used to receive images taken by the drone and convert them into AR images; A maintenance robot that is connected to the AR system and has a multi-angle camera function; The main control console is used to display the AR real scene in the field of view of the drone and maintenance robot; The AR-based reservoir inspection method is executed by a main control console and includes: Controlling the movement of the maintenance robot, when the field of vision of the maintenance robot captures the current circular magnetic sheet (12), determining the position of the maintenance robot in the AR real scene based on the current circular magnetic sheet (12), and controlling the maintenance robot to move to the target position based on the positions of the maintenance robot and the target position in the AR real scene; The steps to create an AR scene include: The drone is controlled to travel along the inspection route, photograph and obtain the real scene of the reservoir, and a plurality of circular magnetic sheets (12) are regularly arranged and attached to the road surface and the surface of the reservoir equipment along the way through a patch mechanism (1); A magnetic sheet coordinate system is established based on the arrangement positions of a plurality of circular magnetic sheets (12), and the reservoir real scene data taken by the drone and the magnetic sheet coordinate system data are transmitted to the AR system to establish an AR real scene.
2. The reservoir inspection method based on AR according to claim 1 is characterized in that: The drone is controlled to travel along the inspection route, photograph and obtain the real scene of the reservoir, and a plurality of circular magnetic sheets (12) are regularly arranged and attached to the road surface and the surface of the reservoir equipment along the way through a patch mechanism (1), including: The drone is controlled to travel along the maintenance route of the maintenance robot, and real scenes around the maintenance route are photographed during the travel process. Circular magnetic sheets (12) are sequentially attached along the maintenance route of the maintenance robot, wherein some of the maintenance routes extend to reservoir equipment, and the drone is controlled to sequentially attach circular magnetic sheets (12) to the reservoir equipment.
3. The reservoir inspection method based on AR according to claim 1 is characterized in that: A magnetic sheet coordinate system is established based on the arrangement positions of a plurality of circular magnetic sheets (12), and the reservoir real scene data taken by the drone and the magnetic sheet coordinate system data are transmitted to the AR system to establish an AR real scene, including: The distance difference and height difference between the circular magnetic sheets (12) are digitized, and a magnetic sheet coordinate system is established with the initial circular magnetic sheet (12) as the coordinate origin. The reservoir real scene is digitized and converted into AR real scene data through three-dimensional modeling. The AR real scene data is correspondingly combined with the magnetic sheet coordinate system to generate an AR real scene with coordinate basis.
4. The reservoir inspection method based on AR according to claim 1 is characterized in that: The method comprises: determining the position of the maintenance robot in the AR real scene based on the current circular magnetic sheet (12); and controlling the maintenance robot to move to the target position based on the positions of the maintenance robot and the target position in the AR real scene. The AR real scene displays a panoramic view of the reservoir. When the maintenance robot recognizes the circular magnetic sheet (12) on the ground, it obtains the coordinates of the maintenance robot in the magnetic sheet coordinate system, and formulates a moving instruction for the maintenance robot based on the coordinates of the maintenance robot and the coordinates of the target position. When the maintenance robot moves to the target position, the maintenance robot obtains an updated partial AR real scene of the equipment by closely recognizing the circular magnetic sheet (12) of the reservoir equipment, and performs simple maintenance operations on the reservoir equipment based on the AR real scene.
5. The reservoir inspection method based on AR according to claim 1 is characterized in that: The method comprises: determining the position of the maintenance robot in the AR real scene based on the current circular magnetic sheet (12); and controlling the maintenance robot to move to the target position based on the positions of the maintenance robot and the target position in the AR real scene. When the maintenance robot recognizes the circular magnetic sheet (12) on the ground, the coordinates of the maintenance robot in the magnetic sheet coordinate system are obtained. At this time, the AR system generates a pre-modeled AR real scene within the field of view of the maintenance robot according to the coordinates of the maintenance robot. At this time, the maintenance robot is controlled to move to the target position with reference to the AR real scene. When the maintenance robot moves to the target position, the maintenance robot obtains an updated local AR real scene of the equipment by identifying the circular magnetic sheet (12) of the reservoir equipment at close range, and performs simple maintenance operations on the reservoir equipment based on the AR real scene.
6. The reservoir inspection method based on AR according to claim 1 is characterized in that: The reservoir inspection system also includes an unmanned boat, which is connected to the AR system and has a multi-angle camera function; The AR-based reservoir inspection method further includes: The main control console controls the movement of the unmanned boat. When the field of vision of the unmanned boat captures the current circular magnetic sheet (12), the position of the unmanned boat in the AR real scene is determined based on the current circular magnetic sheet (12), and the unmanned boat is controlled to move to the target position based on the positions of the unmanned boat and the target position in the AR real scene.
7. A reservoir inspection system, characterized in that: include: A drone has a multi-angle photography function and a patch mechanism (1) is installed at the bottom. The patch mechanism (1) comprises a hollow cylindrical tube (11) and a linear reciprocating mechanism (13). The hollow cylindrical tube (11) is provided with a side straight groove. A plurality of circular magnetic sheets (12) are arranged and placed in the hollow cylindrical tube (11). The linear reciprocating mechanism (13) is installed on the outer wall of the hollow cylindrical tube (11) and is used to push the circular magnetic sheets (12) out of the hollow cylindrical tube (11) in sequence through the side straight groove. The hollow cylindrical tube (11) is installed at the bottom of the drone. An AR system, which is used to receive images taken by the drone and convert them into AR images; A maintenance robot that is connected to the AR system and has a multi-angle camera function; The main control console is used to display the AR real scene in the field of view of the drone and maintenance robot.
8. The reservoir inspection system according to claim 7, characterized in that: It also includes an unmanned boat, on which an omnidirectional camera is installed, and the omnidirectional camera is communicatively connected with the AR system and the main control console.
9. The reservoir inspection system according to claim 7, characterized in that: An omnidirectional camera is installed on the maintenance robot, and the omnidirectional camera communicates with the AR system and is connected to the main control console.
10. The reservoir inspection system according to claim 7, characterized in that: The linear reciprocating mechanism (13) comprises a linear motor (131), an electromagnet (132) and a card (133); the linear motor (131) is fixedly mounted on the outer wall of the hollow cylindrical tube (11); the electromagnet (132) is fixed at the end of the moving end of the linear motor (131) and is directly opposite to the side straight groove of the hollow cylindrical tube (11); and the card (133) is fixed at the bottom end of the side straight groove of the hollow cylindrical tube (11) and is used to separate the circular magnetic sheet (12) from the electromagnet (132).