Equipment inspection method and system based on rail-mounted intelligent inspection robot

Abstract

The invention provides an equipment inspection method and system based on a rail-mounted intelligent inspection robot. The method comprises the following steps: acquiring high-precision map data of an inspection area; according to the inspection task, an inspection sub-task for each inspected device is determined, wherein the inspection sub-task comprises a plurality of target inspection surfaces of the corresponding inspected device; determining a plurality of inspection point locations according to a planned inspection path, the position distribution data of each inspected device and the inspection subtask of each inspected device, wherein each inspection point location is located on the planned inspection path; and controlling the hanging rail intelligent inspection robot to shoot one piece of image data corresponding to the plurality of inspected devices at each inspection point position, and completing inspection of the plurality of inspected devices according to the image data. According to the invention, the inspection point location for simultaneously inspecting a plurality of inspected equipment based on the data of one image is realized, the shooting quantity of the image data of the rail-mounted intelligent inspection robot can be reduced, and the inspection efficiency of the rail-mounted intelligent inspection robot is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of inspection robots, and in particular to an equipment inspection method and system based on a rail-hanging intelligent inspection robot. Background Art

[0002] Inspection robots are divided into track-type and non-track-type, and the track-type is further divided into ground track-type and suspended track-type. Due to the equipment placement in the inspection area, the reservation of the channel area, etc., the suspended track-type inspection robot (hanging track intelligent inspection robot) runs along the suspended track, does not rely on the ground environment, can climb slopes autonomously, and has its own liftable pan / tilt and high-definition camera, which is very suitable for inspections in narrow or complex areas.

[0003] However, the inspection strategy of the existing rail-mounted intelligent inspection robot still has a lot of room for optimization, mainly reflected in the need to capture multiple image data of each inspected device at multiple points to complete the inspection of each inspected device. There is a lack of combined inspection strategies for adjacent inspected devices, resulting in low inspection efficiency. Summary of the invention

[0004] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides an equipment inspection method, system, electronic equipment, computer storage medium and computer program product based on a rail-hanging intelligent inspection robot.

[0005] The present invention provides an equipment inspection method based on a rail-hanging intelligent inspection robot, the method comprising the following steps: Obtain high-precision map data of the inspection area, wherein the high-precision map data includes location distribution data of each inspected device; Determine inspection subtasks for each inspected device according to the inspection task, wherein the inspection subtasks include several target inspection surfaces of the corresponding inspected device; According to the planned inspection route, the location distribution data of each inspected device, and the inspection subtask of each inspected device, a number of inspection points are determined, each of which is located on the planned inspection route; The rail-mounted intelligent inspection robot is controlled to capture a piece of image data corresponding to the plurality of inspected devices at each of the inspection points, and the inspection of the plurality of inspected devices is completed according to the image data.

[0006] Optionally, the rail-hanging intelligent inspection robot is configured with a conventional camera and / or an infrared camera for inspecting the inspected equipment.

[0007] Optionally, the inspection subtask for each inspected device is determined according to the inspection task, and the inspection subtask includes several target inspection surfaces of the corresponding inspected device, including: Parsing the inspection task to obtain the inspection subtask for each inspected device; A plurality of target inspection surfaces are determined according to the device attributes of each inspected device and the inspection subtasks.

[0008] Optionally, the determining of a plurality of target inspection surfaces according to the device attributes of each inspected device and the inspection subtasks includes: Retrieving installation layout location data of each component on the corresponding inspected device according to the device attributes, and determining a number of target components from each component according to the inspection subtask; A plurality of target inspection surfaces are determined based on the installation and layout position data of each target component on the inspected equipment.

[0009] Optionally, the determining of a number of inspection points according to the planned inspection route, the location distribution data of each inspected device, and the inspection subtask of each inspected device includes: Determine the orientation data of each of the target inspection surfaces according to the position distribution data of the inspected equipment, and calculate a number of inspection intervals in which each of the inspected equipment and the planned inspection path have an orientation intersection according to the orientation data, and the inspection intervals are located on the planned inspection path; A potential inspection point is selected in the inspection interval, and the maximum image area of ​​all the target inspection surfaces corresponding to the potential inspection point is calculated according to the single field of view of the rail-hanging intelligent inspection robot; The potential inspection point corresponding to the maximum image area is determined as the inspection point.

[0010] Optionally, selecting a potential inspection point in the inspection interval includes: Determine the intersection interval of each inspection interval, and select a potential inspection point on the intersection interval.

[0011] The present invention also provides an equipment inspection system based on a rail-mounted intelligent inspection robot, the system comprising a rail-mounted intelligent inspection robot and a controller, the controller being used to control the rail-mounted intelligent inspection robot, and specifically implementing the following steps by calling a computer program: Obtain high-precision map data of the inspection area, wherein the high-precision map data includes location distribution data of each inspected device; Determine inspection subtasks for each inspected device according to the inspection task, wherein the inspection subtasks include several target inspection surfaces of the corresponding inspected device; According to the planned inspection route, the location distribution data of each inspected device, and the inspection subtask of each inspected device, a number of inspection points are determined, each of which is located on the planned inspection route; The rail-mounted intelligent inspection robot is controlled to capture a piece of image data corresponding to the plurality of inspected devices at each of the inspection points, and the inspection of the plurality of inspected devices is completed according to the image data.

[0012] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute any of the methods described above.

[0013] The present invention also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, any of the above methods is executed.

[0014] The present invention also provides a computer program product, which includes a computer program stored in a computer storage medium, and when the computer program is executed by a processor of an electronic device, it implements any of the methods described above.

[0015] The present invention determines the inspection points at which multiple inspected devices can be inspected simultaneously based on one image data through the planned inspection path, the location distribution data of each inspected device, and the inspection sub-task of each inspected device. This can reduce the number of image data captured by the rail-mounted intelligent inspection robot and significantly improve the inspection efficiency of the rail-mounted intelligent inspection robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a schematic diagram of an equipment inspection method based on a rail-hanging intelligent inspection robot disclosed in an embodiment of the present invention.

[0018] Figure 2 It is a schematic diagram of the inspection interval of the present invention.

[0019] Figure 3 It is a schematic diagram of an equipment inspection system based on a rail-hanging intelligent inspection robot disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0021] See also Figure 1 The embodiment of the present invention discloses an equipment inspection method based on a rail-hanging intelligent inspection robot, the method comprising the following steps: Obtain high-precision map data of the inspection area, wherein the high-precision map data includes location distribution data of each inspected device; Determine inspection subtasks for each inspected device according to the inspection task, wherein the inspection subtasks include several target inspection surfaces of the corresponding inspected device; According to the planned inspection route, the location distribution data of each inspected device, and the inspection subtask of each inspected device, a number of inspection points are determined, each of which is located on the planned inspection route; The rail-mounted intelligent inspection robot is controlled to capture a piece of image data corresponding to the plurality of inspected devices at each of the inspection points, and the inspection of the plurality of inspected devices is completed according to the image data.

[0022] The existing track-mounted intelligent inspection robot only captures image data for a single inspected device each time, and needs to capture images of the inspected device from as many perspectives as possible at multiple points, resulting in low inspection efficiency and a large consumption of inspection computing power.

[0023] In view of the above technical problems, the present invention is configured to first obtain high-precision map data of the inspection area, and the high-precision map data contains the location distribution data of all inspected devices. Then, the inspection subtasks for each inspected device are parsed from the received inspection tasks, and the inspection subtasks include several target inspection surfaces of the corresponding inspected device (for example, two of the four surfaces of the inspected device are inspected), and each target inspection surface corresponds to a shooting angle of the inspected device; and the planned inspection path constrained by the hanging track is also known. Therefore, a comprehensive analysis is performed based on the planned inspection path, the location distribution data of each inspected device, and the inspection subtasks of each inspected device, and several inspection points are screened on the planned inspection path. The hanging track intelligent inspection robot can only shoot one image data containing multiple inspected devices at each inspection point, and then realize the simultaneous inspection of multiple inspected devices based on the image data, that is, extract the specific features of multiple inspected devices from the image data, and then realize the inspection of the corresponding items.

[0024] Therefore, the present invention determines the inspection points that can realize simultaneous inspection of multiple inspected devices based on one image data through the planned inspection path, the location distribution data of each inspected device, and the inspection sub-task of each inspected device. This can reduce the number of image data captured by the rail-mounted intelligent inspection robot and significantly improve the inspection efficiency of the rail-mounted intelligent inspection robot.

[0025] Optionally, the rail-hanging intelligent inspection robot is configured with a conventional camera and / or an infrared camera for inspecting the inspected equipment.

[0026] In this embodiment, in view of the different inspection tasks, the rail-mounted intelligent inspection robot will need to use different types of cameras to capture image data of the inspected equipment during the inspection process, such as conventional cameras and / or infrared cameras. Among them, conventional cameras refer to cameras that use CCD (Charge-Coupled Device) or CMOS (Complementary Metal-Oxide Semiconductor) as image sensors. Infrared cameras refer to cameras that emit infrared light to supplement the monitoring scene and form an image, or rely on the infrared thermal radiation of the detected object itself to achieve imaging.

[0027] When the inspection task includes inspection of abnormal heating of electrical equipment, it is obviously necessary to use an infrared camera, while when the inspection task includes foreign body recognition and inspection of switch status of electrical equipment, a conventional camera can be used. Of course, the conventional camera and the infrared camera can also be controlled to capture image data at the same inspection point at the same time, that is, the aforementioned image data can be two different types of image data.

[0028] Optionally, the inspection subtask for each inspected device is determined according to the inspection task, and the inspection subtask includes several target inspection surfaces of the corresponding inspected device, including: Parsing the inspection task to obtain the inspection subtask for each inspected device; A plurality of target inspection surfaces are determined according to the device attributes of each inspected device and the inspection subtasks.

[0029] In this embodiment, the staff or the automatic inspection system can formulate the inspection tasks for each device in the target area in advance according to the preset rules, and the inspection tasks include inspection subtasks involving each inspected device. After receiving the inspection task, the rail-mounted intelligent inspection robot parses and processes it, and obtains the inspection subtasks of each inspected device contained therein. At the same time, the device attributes of each inspected device are determined, and according to the device attributes of the inspected device and the inspection subtasks of the inspected device, it can be analyzed which viewing angles of the inspected device need to be inspected, that is, the target inspection surface is determined. For example, when the inspection subtask is the inspection of the opening and closing status of the knife, the A surface of the inspected device is determined as the target inspection surface, and when the inspection subtask is the inspection of abnormal temperature, the AC surface of the inspected device is determined as the target inspection surface.

[0030] Optionally, the determining of a plurality of target inspection surfaces according to the device attributes of each inspected device and the inspection subtasks includes: Retrieving installation layout location data of each component on the corresponding inspected device according to the device attributes, and determining a number of target components from each component according to the inspection subtask; A plurality of target inspection surfaces are determined based on the installation and layout position data of each target component on the inspected device.

[0031] In this embodiment, the three-dimensional structural data of each inspected device is pre-stored in the database, and the three-dimensional structural data includes the installation layout position data of each component. For example, a certain inspected device includes a high-power motor, an automatic knife switch, a high-pressure air pipe, etc. The high-power motor is located in the middle position inside, and the automatic knife switch is located on the outer B panel of the inspected device. The high-pressure air pipe extends from the outer C panel of the inspected device to the outside to connect with other devices. At the same time, by further analyzing the corresponding inspection subtasks obtained by the above-mentioned analysis, the target components involved in this inspection can be determined from the above-mentioned components of the inspected device. Therefore, according to the installation layout position data of these target components on the inspected device, several target inspection surfaces of the inspected device can be determined. Examples are as follows: The inspection subtask is to inspect the temperature anomaly of the inspected equipment. Among the inspected equipment, only the high-power motor and the automatic switch (for example, when short-circuited) may have temperature anomaly, so the high-power motor and the automatic switch are determined as target devices. Since the high-power motor is located in the middle of the inspected equipment, the AC side panel of the inspected equipment facing the hanging track is determined as the target inspection surface, and the automatic switch is located on the outer B panel of the inspected equipment, so the AC surface of the inspected equipment facing the hanging track is finally determined as the target inspection surface.

[0032] Alternatively, the inspection subtask is specifically to inspect the inspected equipment for abnormal air leakage, and among the inspected equipment, only the high-pressure air pipe has the possibility of abnormal air leakage, so the high-pressure air pipe is determined as the target device, and then the outer C panel where the high-pressure air pipe is located is determined as the target inspection surface.

[0033] Optionally, the determining of a number of inspection points according to the planned inspection route, the location distribution data of each inspected device, and the inspection subtask of each inspected device includes: Determine the orientation data of each of the target inspection surfaces according to the position distribution data of the inspected equipment, and calculate a number of inspection intervals in which each of the inspected equipment and the planned inspection path have an orientation intersection according to the orientation data, and the inspection intervals are located on the planned inspection path; A potential inspection point is selected in the inspection interval, and the maximum image area of ​​all the target inspection surfaces corresponding to the potential inspection point is calculated according to the single field of view of the rail-hanging intelligent inspection robot; The potential inspection point corresponding to the maximum image area is determined as the inspection point.

[0034] In this embodiment, since the distribution direction of each target inspection surface on the inspected device is known (derived from the three-dimensional structure data), the orientation data of each target inspection surface of the inspected device can be obtained based on the position distribution data of the inspected device. At the same time, the direction and position of the planned inspection path are known, and based on this, the inspection intervals of these target inspection surfaces and the planned inspection path can be obtained based on the orientation data of all target inspection surfaces of the inspected device. The inspection interval refers to the intersection of the intersection area of ​​each target inspection surface and the planned inspection path, such as Figure 2 1-3 interval, 2-4 interval. Then, a potential inspection point is randomly selected in the inspection interval, and the maximum image area of ​​all target inspection surfaces (involving the target inspection surfaces of all inspected devices in the single field of view) corresponding to the potential inspection point is calculated according to the single field of view of the rail-hanging intelligent inspection robot (that is, the field of view of the camera equipped with the rail-hanging intelligent inspection robot), and the potential inspection point corresponding to the maximum value of the maximum image area is determined as the final inspection point. By analogy, multiple inspection points are determined on the planned inspection path.

[0035] Optionally, selecting a potential inspection point in the inspection interval includes: Determine the intersection interval of each inspection interval, and select a potential inspection point on the intersection interval.

[0036] In this embodiment, one inspected device corresponds to one inspection interval on the planned inspection path, such as Figure 2The inspection intervals of adjacent inspected devices may overlap, such as Figure 2 The 2-3 interval in the intersection is selected, and potential inspection points are selected in this intersection interval. This can narrow the scope of inspection point determination and is conducive to quickly determining the inspection points.

[0037] It should be noted that the inspection points determined by the above method can realize the inspection of most adjacent inspected devices based on one image data, but due to the mismatch between the location distribution data of some inspected devices and the planned inspection path, there will always be some inspected devices that do not have the corresponding inspection points mentioned above, and thus the inspection cannot be completed based on one image data taken at one inspection point. For these inspected devices, a separate inspection method can be adopted, that is, one or more corresponding inspection points are determined for these inspected devices on the planned inspection path, and the inspection corresponding to the inspection subtask is completed based on one or more image data taken.

[0038] See also Figure 3 As shown, an embodiment of the present invention further provides an equipment inspection system based on a rail-mounted intelligent inspection robot, the system comprising a rail-mounted intelligent inspection robot and a controller, the controller being used to control the rail-mounted intelligent inspection robot, and specifically implementing the following steps by calling a computer program: Obtain high-precision map data of the inspection area, wherein the high-precision map data includes location distribution data of each inspected device; Determine inspection subtasks for each inspected device according to the inspection task, wherein the inspection subtasks include several target inspection surfaces of the corresponding inspected device; According to the planned inspection route, the location distribution data of each inspected device, and the inspection subtask of each inspected device, a number of inspection points are determined, each of which is located on the planned inspection route; The intelligent inspection robot is controlled to capture a piece of image data corresponding to the plurality of inspected devices at each inspection point, and the inspection of the plurality of inspected devices is completed according to the image data. An embodiment of the present invention further provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method described in any of the above embodiments.

[0039] An embodiment of the present invention further provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in any of the above embodiments is executed.

[0040] An embodiment of the present invention further provides a computer program product, which includes a computer program stored in a computer storage medium, and when the computer program is executed by a processor of an electronic device, the method described in any of the above embodiments is implemented.

[0041] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0042] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0043] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0044] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An equipment inspection method based on a rail-hanging intelligent inspection robot, characterized in that: The method comprises the following steps: Obtain high-precision map data of the inspection area, wherein the high-precision map data includes location distribution data of each inspected device; Determine inspection subtasks for each inspected device according to the inspection task, wherein the inspection subtasks include several target inspection surfaces of the corresponding inspected device; According to the planned inspection route, the location distribution data of each inspected device, and the inspection subtask of each inspected device, a number of inspection points are determined, each of which is located on the planned inspection route; The rail-mounted intelligent inspection robot is controlled to capture a piece of image data corresponding to the plurality of inspected devices at each of the inspection points, and the inspection of the plurality of inspected devices is completed according to the image data.

2. According to claim 1, a method for equipment inspection based on a rail-hanging intelligent inspection robot is characterized in that: The rail-hanging intelligent inspection robot is equipped with a conventional camera and / or an infrared camera for inspecting the inspected equipment.

3. The equipment inspection method based on the rail-hanging intelligent inspection robot according to claim 2 is characterized in that: According to the inspection task, an inspection subtask for each inspected device is determined, and the inspection subtask includes several target inspection surfaces of the corresponding inspected device, including: Parsing the inspection task to obtain the inspection subtask for each inspected device; A plurality of target inspection surfaces are determined according to the device attributes of each inspected device and the inspection subtasks.

4. The equipment inspection method based on the rail-hanging intelligent inspection robot according to claim 3 is characterized in that: According to the device attributes of each inspected device and the inspection subtask, a number of target inspection surfaces are determined, including: Retrieving installation layout location data of each component on the corresponding inspected device according to the device attributes, and determining a number of target components from each component according to the inspection subtask; A plurality of target inspection surfaces are determined based on the installation and layout position data of each target component on the inspected equipment.

5. The equipment inspection method based on the rail-hanging intelligent inspection robot according to claim 4 is characterized in that: According to the planned inspection route, the location distribution data of each inspected device, and the inspection subtasks of each inspected device, several inspection points are determined, including: Determine the orientation data of each of the target inspection surfaces according to the position distribution data of the inspected equipment, and calculate a number of inspection intervals in which each of the inspected equipment and the planned inspection path have an orientation intersection according to the orientation data, and the inspection intervals are located on the planned inspection path; A potential inspection point is selected in the inspection interval, and the maximum image area of ​​all the target inspection surfaces corresponding to the potential inspection point is calculated according to the single field of view of the rail-hanging intelligent inspection robot; The potential inspection point corresponding to the maximum image area is determined as the inspection point.

6. The equipment inspection method based on the rail-hanging intelligent inspection robot according to claim 5 is characterized in that: Selecting a potential inspection point in the inspection interval includes: Determine the intersection interval of each inspection interval, and select a potential inspection point on the intersection interval.

7. An equipment inspection system based on a rail-mounted intelligent inspection robot, the system comprising a rail-mounted intelligent inspection robot and a controller, characterized in that: The controller is used to control the rail-hanging intelligent inspection robot, and specifically implements the following steps by calling a computer program: Obtain high-precision map data of the inspection area, wherein the high-precision map data includes location distribution data of each inspected device; Determine inspection subtasks for each inspected device according to the inspection task, wherein the inspection subtasks include several target inspection surfaces of the corresponding inspected device; According to the planned inspection route, the location distribution data of each inspected device, and the inspection subtask of each inspected device, a number of inspection points are determined, each of which is located on the planned inspection route; The rail-mounted intelligent inspection robot is controlled to capture a piece of image data corresponding to the plurality of inspected devices at each of the inspection points, and the inspection of the plurality of inspected devices is completed according to the image data.

8. An electronic device comprising: A memory storing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-6.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is executed.

10. A computer program product, comprising a computer program stored in a computer storage medium, characterized in that: When the computer program is executed by a processor of an electronic device, the method according to any one of claims 1 to 6 is implemented.

Images