Defect detection method and system for nuclear power building and electronic equipment

Abstract

The invention is suitable for the technical field of nuclear power, and provides a defect detection method and system for a nuclear power building and electronic equipment, and the method comprises the steps: obtaining three-dimensional point cloud data of an annular corridor; constructing a three-dimensional point cloud model of the annular gallery according to the three-dimensional point cloud data; generating a task route according to the three-dimensional point cloud model; the task route is sent to an aircraft so that the aircraft can execute a close flight task according to the task route, and propellers and / or fan blades of the aircraft are / is installed in a duct; receiving data sent by the aircraft, wherein the data comprises image data obtained by shooting the surface of the containment of the annular corridor by the aircraft; and performing defect detection on the surface of the containment vessel according to the image data. Through the method, the detection efficiency can be improved, and the safety risk of people can be reduced.

Description

Technical Field

[0001] The present application belongs to the field of nuclear power technology, and in particular relates to a defect detection method, system, device, electronic equipment, computer-readable storage medium, and computer program product for nuclear power buildings. Background Art

[0002] The nuclear power unit is the core component of a nuclear power plant. Its basic working principle is to make the nuclear fuel undergo fission reaction in the nuclear reactor, releasing a large amount of heat energy, and then convert the heat energy into steam through a heat exchanger to drive the steam turbine to rotate, and finally drive the generator to generate electricity.

[0003] With the advancement of nuclear power technology, the structural design of nuclear power plants has also evolved accordingly. For example, third-generation nuclear power plants feature a double-containment design, a massive concrete structure with an extremely high safety rating. The inner containment, with a diameter of 48.2 meters, serves as the plant's final safety barrier, primarily preventing the escape of radioactive materials produced by nuclear fission. The outer containment, with a diameter of 53 meters, provides protection against impacts and explosions from large aircraft. Between the two containment structures, a circular corridor is formed, only 1.2 to 1.8 meters wide and nearly 60 meters high (each corridor is approximately 155 meters high). Because this corridor is a radiation-controlled area, it houses numerous equipment, piping, steel supports, grid platforms, firebreaks, and other facilities, resulting in a confined and complex environment.

[0004] According to upstream regulations, the inner containment of a double containment, a critical structure for ensuring nuclear power production safety, must possess excellent sealing and stability. Regular preventative defect inspections are essential to assess the structural safety performance and ensure nuclear safety. Currently, due to the narrowness of the annular corridor, the primary approach to double containment defect inspection relies on manual close-up inspections. Specifically, scaffolding platforms or stepladders are constructed within the inherent steel grating floors (approximately 6-10 meters high) within the annular corridor between the double containment shells, allowing for manual close-up inspections close to the walls. Because the containment area to be inspected for a single project exceeds 30,000 square meters, a significant amount of scaffolding is required. This large area also creates a significant inspection workload. Furthermore, the presence of manual inspections within a radiation-controlled area during inner containment inspections presents certain safety risks. Consequently, existing methods for inner containment defect inspections are time-consuming, inefficient, and pose significant safety risks. Summary of the Invention

[0005] The embodiments of the present application provide a method, system, and electronic equipment for defect detection in nuclear power buildings, which can solve the problems of low efficiency and high safety risks of existing containment vessel detection.

[0006] In a first aspect, an embodiment of the present application provides a method for detecting defects in a nuclear power building, wherein the structure of the nuclear power building includes a double-layer containment structure, wherein an annular corridor is formed in the middle of the double-layer containment structure. The method for detecting defects in the nuclear power building includes:

[0007] Acquiring three-dimensional point cloud data of the annular corridor;

[0008] Constructing a three-dimensional point cloud model of the annular corridor according to the three-dimensional point cloud data;

[0009] generating a mission route according to the three-dimensional point cloud model;

[0010] sending the mission route to an aircraft so that the aircraft performs a close-flight mission according to the mission route, wherein a propeller and / or fan blade of the aircraft is installed inside a duct;

[0011] receiving data sent by the aircraft, the data including image data obtained by the aircraft photographing the containment surface of the annular corridor;

[0012] Defect detection is performed on the surface of the containment vessel according to the image data.

[0013] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0014] In an embodiment of the present application, after acquiring 3D point cloud data of an annular corridor, a 3D point cloud model of the annular corridor is constructed based on the 3D point cloud data, and a mission route is generated based on the 3D point cloud model. After transmitting the mission route to an aircraft, data is received from the aircraft, including image data of the containment surface captured by the aircraft in the annular corridor, and defect detection is performed on the containment surface based on the image data. Since the 3D point cloud model of the annular corridor has been constructed, a corresponding mission route can be generated based on the 3D point cloud model. Once the aircraft obtains image data of the containment surface based on the mission route, defect detection can be performed on the containment surface based on the image data captured by the aircraft. Because defect detection on the containment surface does not require the construction of a scaffolding platform or close-up inspection of the containment surface, inspection efficiency is improved and safety risks are reduced. Furthermore, since the aircraft's propellers and / or fan blades are mounted inside the duct, even if the aircraft flies through the annular corridor, their propellers and / or fan blades will not directly damage the containment surface.

[0015] In a second aspect, an embodiment of the present application provides a defect detection system for a nuclear power building, wherein the structure of the nuclear power building includes a double-layer containment structure, wherein a ring corridor is formed in the middle of the double-layer containment structure. The defect detection system for the nuclear power building includes: a point cloud data acquisition device, a ground station, and an aircraft;

[0016] The point cloud data acquisition device is used to collect three-dimensional data of the annular corridor to obtain three-dimensional point cloud data of the annular corridor;

[0017] The ground station is configured to acquire three-dimensional point cloud data of the annular corridor, construct a three-dimensional point cloud model of the annular corridor based on the three-dimensional point cloud data, generate a mission route based on the three-dimensional point cloud model, and transmit the mission route to an aircraft, wherein a propeller and / or fan blade of the aircraft is installed inside the duct;

[0018] The aircraft is configured to perform a close flight mission according to the received mission route, photograph the containment surface of the annular corridor, obtain image data, and transmit data including the image data to the ground station;

[0019] The ground station is further configured to receive data sent by the aircraft and perform defect detection on the containment surface based on the image data.

[0020] In a third aspect, an embodiment of the present application provides a defect detection device for a nuclear power building, wherein the structure of the nuclear power building includes a double-layer containment structure, wherein an annular corridor is formed in the middle of the double-layer containment structure, and the defect detection device for the nuclear power building includes:

[0021] A three-dimensional point cloud data acquisition module, used to acquire three-dimensional point cloud data of the annular corridor;

[0022] A three-dimensional point cloud model construction module, configured to construct a three-dimensional point cloud model of the annular corridor based on the three-dimensional point cloud data;

[0023] A mission route generation module, configured to generate a mission route based on the three-dimensional point cloud model;

[0024] a mission route sending module, configured to send the mission route to an aircraft, so that the aircraft performs a close flight mission according to the mission route, wherein the propeller and / or fan blades of the aircraft are installed inside the duct;

[0025] a data receiving module, configured to receive data sent by the aircraft, wherein the data includes image data obtained by the aircraft photographing the surface of the containment vessel of the annular corridor;

[0026] A defect detection module is used to perform defect detection on the surface of the containment shell according to the image data.

[0027] In a fourth aspect, an embodiment of the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0028] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0029] In a sixth aspect, an embodiment of the present application provides a computer program product, which, when executed on an electronic device, enables the electronic device to execute the method described in the first aspect above.

[0030] It can be understood that the beneficial effects of the second to sixth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art.

[0032] Figure 1 This is a flow chart of a method for defect detection in a nuclear power building provided in one embodiment of the present application;

[0033] Figure 2 This is a schematic structural diagram of a defect detection system for a nuclear power building provided by an embodiment of the present application;

[0034] Figure 3 1 is a schematic diagram of a frame structure of a dual-ducted UAV provided in one embodiment of the present application;

[0035] Figure 4 This is a schematic diagram of a processing flow of a defect detection system for a nuclear power building provided by an embodiment of the present application;

[0036] Figure 5 This is a structural schematic diagram of a defect detection device for a nuclear power building provided by another embodiment of the present application;

[0037] Figure 6 This is a structural diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0038] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0039] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0040] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0041] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in yet other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized.

[0042] Currently, third-generation nuclear power plants primarily utilize a double-containment design. To improve safety during operation, the containment surface of the double-containment needs to be inspected. Given the narrowness of the central annular corridor within the double-containment and the presence of other obstacles, surface inspections are typically performed manually, using scaffolding platforms or stepladders, close to the wall. However, these methods are time-consuming, inefficient, and pose significant safety risks to the inspectors.

[0043] In order to improve detection efficiency and reduce the safety risks brought about by detection, an embodiment of the present application provides a defect detection method for nuclear power buildings.

[0044] The defect detection method for nuclear power buildings provided in an embodiment of the present application is described below with reference to the accompanying drawings.

[0045] Figure 1A schematic flow chart of a defect detection method for a nuclear power building provided in an embodiment of the present application is shown. In this embodiment of the present application, the nuclear power building structure includes a double-layer containment structure consisting of an inner containment shell and an outer containment shell, with an annular corridor formed in the middle of the double-layer containment shell. The defect detection method for a nuclear power building provided in this embodiment of the present application can be applied to a ground station, which can be an electronic device capable of performing three-dimensional point cloud data processing, as detailed below:

[0046] S11, obtaining three-dimensional point cloud data of the circular corridor.

[0047] Specifically, a 3D laser scanner can be used to scan the annular corridor (e.g., the outer surface of the inner shell, the inner surface of the outer shell, obstacles between the inner and outer shells, etc.) to obtain 3D point cloud data of the annular corridor. Alternatively, 3D point cloud data of the annular corridor can be obtained using a depth camera or binocular vision. Of course, other devices can also be used to obtain data, which will not be detailed here.

[0048] In this embodiment of the present application, the 3D point cloud data of the annular corridor includes position information corresponding to sampling points on the outer surface of the inner shell, the inner surface of the outer shell, obstacles between the inner and outer shells, and other surfaces. This 3D point cloud data may also include color information, reflectivity, etc. Optionally, to improve the accuracy of the acquired 3D point cloud data, the 3D point cloud data of the annular corridor may be acquired after it is determined that the nuclear power building has no defects. For example, the 3D point cloud data of the annular corridor of the nuclear power building may be acquired after the nuclear power building has been inspected and accepted.

[0049] Alternatively, considering that it is difficult to collect all the 3D point cloud data corresponding to the circular corridor using a single viewing angle, the circular corridor can be divided into multiple detection areas, and then the 3D point cloud data of each detection area can be obtained separately. That is, when obtaining the 3D point cloud data of the circular corridor, it includes:

[0050] The annular corridor is divided into a plurality of detection areas, and three-dimensional point cloud data of each of the detection areas is acquired, thereby obtaining three-dimensional point cloud data of the annular corridor, wherein each detection area is provided with at least one positioning target.

[0051] The positioning target is a reference object used for positioning and measurement. It typically has a unique geometric shape or coded information (such as location information) to facilitate identification and positioning by detection equipment (such as cameras and laser scanners). Common positioning targets include checkerboard targets, circular targets, coded targets, spherical targets, and paper prism targets.

[0052] For each inspection area, 3D point cloud data can be collected from a single viewing angle. For example, a 3D laser scanner can scan an inspection area within a fixed viewing angle to obtain 3D point cloud data corresponding to the inspection area.

[0053] Optionally, when dividing the detection area, the annular corridor can be divided according to at least one of the following reference information: the position of the buttress structure set in the annular corridor, the transmission distance of the signal in the annular corridor, the visibility and the number of layers divided by the grid platform into the above annular corridor.

[0054] Line of sight refers to whether the line of sight between two points is unobstructed, that is, whether there are any obstacles blocking the line of sight. If the line of sight is not blocked by any obstacles, the line of sight is "line of sight", otherwise, the line of sight is "no line of sight".

[0055] In a nuclear power plant, a circular corridor is usually provided with buttress structures protruding from the shell surface at regular intervals. Since the buttress structures protrude from the shell surface, they will obstruct the line of sight, resulting in blindness.

[0056] In the embodiment of the present application, when dividing the detection area, it should be ensured that the detection area is visible and the signal transmission distance can cover the detection area, so as to improve the accuracy of the data subsequently obtained based on the detection area. For example, the height of a nuclear power building with a double-layer containment shell is about 60 meters (m), and it is divided into 7 layers (layer height 6-10m) from top to bottom by a steel grid platform. The circumference of the circular corridor is 152m, and a buttress column structure (width of about 6m) protruding 60cm from the shell surface is set every 48m or so. According to the corridor environment, when measuring the signal transmitted by the aircraft to the ground station, if the unidirectional transmission distance is within 12m (bidirectional transmission distance 24m), the transmission effect is good and the visibility is clear. Assume that the circular corridor on the first floor is divided into four areas by the buttress structure, and among the four areas, there are three areas with a perimeter of 48 meters and one area with a perimeter of 8 meters. Since 48 / 24=2, the three areas with a perimeter of 48 meters should be divided into two sub-areas, and each sub-area serves as a detection area. That is, the circular corridor on the first floor is divided into 2*3+1=7 detection areas, and the circular corridor on the seventh floor is divided into 7*7=49 detection areas.

[0057] Optionally, considering that subsequent aircraft will collect data from the inspection area, the aircraft's flight duration when fully loaded may also be considered when dividing the inspection area. The inspection areas should be divided so that the aircraft can complete data collection for at least one inspection area within its flight duration. For example, if the distance covered by the aircraft's flight duration when fully loaded is less than 24 meters, the circular corridors will be divided based on the distance covered by the flight duration. Since the aircraft's flight duration is also considered when dividing the inspection area, the accuracy of the divided inspection areas can be improved.

[0058] S12: constructing a three-dimensional point cloud model of the circular corridor based on the three-dimensional point cloud data.

[0059] Specifically, a coordinate system is constructed using the nuclear power building corresponding to the annular corridor to obtain a point cloud coordinate system, and a three-dimensional point cloud model of the annular corridor is constructed based on the point cloud coordinate system and the three-dimensional point cloud data.

[0060] Optionally, if the above-mentioned three-dimensional point cloud data is the three-dimensional point cloud data corresponding to each detection area of ​​the annular corridor, the three-dimensional point cloud data of the corresponding detection areas are spliced ​​according to the adjacent relationship of each detection area and the above-mentioned point cloud coordinate system to obtain a complete three-dimensional point cloud model of the annular corridor between the double shells in a unified coordinate system.

[0061] S13, generating a mission route based on the three-dimensional point cloud model.

[0062] Specifically, the system combines the containment surface and obstacle information in the 3D point cloud model to generate a mission route that targets the containment surface and avoids the obstacle information. A mission route is the route that an aircraft flies to collect image data of a containment surface (such as the inner or outer containment surface). Each mission route includes multiple waypoints. When the aircraft reaches a waypoint, it can capture the containment surface and obtain corresponding image data.

[0063] In the embodiment of the present application, when the circular corridor is divided into multiple detection areas, a mission route can be generated for each detection area, or a mission route can be generated for more than one detection area, without limitation. When a mission route is generated based on a three-dimensional point cloud model, the coordinate system in which the waypoints of the mission route are located is the point cloud coordinate system, and the position information corresponding to the waypoints is the position information in the point cloud coordinate system.

[0064] Optionally, the ground station also includes a display screen. The generated mission route is displayed on the display screen. When a user edits the mission route, the displayed mission route is edited based on the edit action. This editing action includes dragging the mission route, adding waypoints, deleting waypoints, and so on. The ability to edit the generated mission route helps improve the accuracy of the resulting mission route.

[0065] S14, sending the mission route to the aircraft, so that the aircraft performs the close flight mission according to the mission route, wherein the propeller and / or fan blades of the aircraft are installed inside the duct.

[0066] The aircraft here refers to equipment that can fly in the air, including drones and rotorcraft.

[0067] In the embodiment of the present application, considering that the aircraft is usually controlled by propellers and / or fan blades, and that the rotating propellers and / or fan blades may cause damage to the containment surface in the annular corridor during the flight of the aircraft in the annular corridor, when the aircraft has a propeller, the propeller is installed inside the duct, and when the aircraft has fan blades, the fan blades are installed inside the duct. Of course, if the aircraft has both propellers and fan blades, the propeller and fan blades are both installed inside the duct. Since the duct wall separates the propeller and / or fan blades from the containment surface, and the duct wall is smoother than the propeller and / or fan blades, using an aircraft with propellers and / or fan blades installed inside the duct to perform close flight missions is beneficial to reducing the probability of the aircraft causing damage to the containment surface in the annular corridor, and the probability of the aircraft colliding with equipment pipes or the containment surface causing damage.

[0068] In an embodiment of the present application, the ground station may transmit the mission route to the aircraft via wireless communication, such as Bluetooth communication, Wireless Fidelity (WiFI), etc. After receiving the mission route, the aircraft may control its flight according to the mission route and, during flight, capture the surface of the containment vessel to obtain corresponding image data.

[0069] Optionally, the ground station can notify the aircraft to perform the corresponding flight mission by sending the mission route to the aircraft (the flight mission is used to instruct the aircraft to fly according to the mission route and perform the corresponding shooting action), or after sending the mission route to the aircraft, the ground station can issue the flight mission to the aircraft, and the aircraft will perform the flight mission after receiving the flight mission.

[0070] Optionally, the ground station also includes a display screen. While the aircraft is performing a close-flight mission, the 3D point cloud model displays the aircraft's current position. Furthermore, the aircraft's current mission route can be displayed, allowing users to promptly monitor the aircraft's current position and its relative deviation from the mission route.

[0071] S15, receiving data sent by the aircraft, wherein the data includes image data obtained by the aircraft photographing the surface of the containment vessel of the annular corridor.

[0072] Specifically, the ground station receives data including image data of the containment surface sent by the aircraft through a wireless communication connection established with the aircraft.

[0073] S16, performing defect detection on the surface of the containment vessel according to the image data.

[0074] Among them, the defect detection here includes crack detection, honeycomb and looseness detection, rough surface detection, peeling detection, exposed reinforcement detection, hole detection, etc.

[0075] In an embodiment of the present application, after acquiring 3D point cloud data of an annular corridor, a 3D point cloud model of the annular corridor is constructed based on the 3D point cloud data, and a mission route is generated based on the 3D point cloud model. After transmitting the mission route to an aircraft, data is received from the aircraft, including image data of the containment surface captured by the aircraft in the annular corridor, and defect detection is performed on the containment surface based on the image data. Since the 3D point cloud model of the annular corridor has been constructed, a corresponding mission route can be generated based on the 3D point cloud model. Once the aircraft obtains image data of the containment surface based on the mission route, defect detection can be performed on the containment surface based on the image data captured by the aircraft. Because defect detection on the containment surface does not require the construction of a scaffolding platform or close-up inspection of the containment surface, inspection efficiency is improved and safety risks are reduced. Furthermore, since the aircraft's propellers and / or fan blades are mounted inside the duct, even if the aircraft flies through the annular corridor, their propellers and / or fan blades will not directly damage the containment surface.

[0076] In some embodiments, considering that the positioning target is easily recognized and located by the detection equipment, the positioning target in the detection area can be used as a route reference point, that is, the above S13, generating a mission route based on the above three-dimensional point cloud model, includes:

[0077] The mission route is generated based on the positioning targets of the detection area in the three-dimensional point cloud model.

[0078] The position of the positioning target in the detection area can be set according to actual conditions. For example, if there is only one positioning target in each detection area and the inner containment needs to be inspected for defects, the positioning target can be uniformly set on the inner containment wall at the leftmost edge of the corresponding detection area (of course, it can also be other positions). Furthermore, considering that the mission route is generated based on the positioning target, and subsequent defect detection will be performed based on the images captured by the aircraft during the flight along the mission route, in order to obtain more comprehensive image data of the inner containment, the positioning target can be set at a position close to the ground, such as setting the positioning target at a height of 1m from the ground. For example, when the positioning target is a paper prism target, the paper prism target can be attached to the wall of the inner containment at the leftmost edge of the detection area and 1m from the ground. Optionally, the size of the paper prism target can be 20cm*20cm.

[0079] Specifically, based on the position information of the positioning targets in the detection area, a mission route is generated that includes the position information of at least one positioning target in the detection area. The position information of the positioning target typically serves as the starting point of the mission route (i.e., the first waypoint of the mission route), but can also serve as one of the waypoints of the mission route. Because positioning targets are easily detected by the aircraft, generating a mission route based on the positioning targets in the detection area is beneficial for improving the accuracy of the generated mission route.

[0080] In the embodiment of the present application, when generating a mission route, the following generation method can be used:

[0081] A1. Determine the positioning target in the detection area in the three-dimensional point cloud model as the starting point of the mission route.

[0082] Specifically, when there is only one positioning target in the detection area, the positioning target can be used as the starting point of the mission route of the detection area; when the detection area includes more than one positioning target, one of the positioning targets can be selected as the starting point of the mission route of the detection area.

[0083] Since the positioning target in the detection area is clearly identifiable, using it as the starting point of the mission route helps the aircraft more quickly determine the starting point of the mission route. Optionally, the aircraft is equipped with a binocular vision system that detects the positioning target to achieve the perception and positioning function.

[0084] A2. Generate the mission route based on the starting point of the mission route and the following conditions: the generated mission route avoids obstacles in the annular corridor, the spatial overlap of image data captured by the aircraft at adjacent waypoints is greater than a preset value, and the distance between the aircraft and the containment surface is within a preset distance range.

[0085] The preset value is greater than or equal to the minimum overlap required when stitching two images. For example, if the minimum overlap required when stitching two images is 35%, the preset value may be set to 35%.

[0086] The preset distance range is defined as follows: when the aircraft performs a shooting action within the preset distance range, the captured image is clear and does not collide with the containment surface or other obstacles. Optionally, 60 cm ≤ the preset distance range < the width between the double containment shells. For example, if the width between the double containment shells is 1.2 m, 60 cm ≤ the preset distance range < 1 m. Optionally, the distance between the aircraft and the containment shell surface is 60 cm.

[0087] In the embodiment of the present application, the heights of the various waypoints in the generated mission route are not necessarily the same, but when the aircraft flies along the mission route from the starting point of the mission route, it can avoid obstacles in the annular corridor, such as the buttress structure of the annular corridor. When the aircraft reaches the waypoint of the mission route and performs the shooting action, the image obtained should be clear enough, such as the image obtained by shooting can clearly reflect the texture or details of the surface of the containment vessel. In addition, the degree of overlap of the image data (or images) obtained by the aircraft at two adjacent waypoints in geographic space (i.e., the degree of overlap of the same object) should be greater than a preset value, so that the images taken at each waypoint can be spliced ​​together to form a spliced ​​image that can reflect the entire detection area.

[0088] Optionally, considering that frontal photography provides higher quality images, the generated mission route should enable the aircraft to capture the inspection area from the front. For example, when the aircraft is in front of the positioning target, the centers of the aircraft, the positioning target, and the double containment vessel should be aligned.

[0089] The above describes how to generate a mission route and, after the aircraft acquires data including image data according to the mission route, perform defect detection on the containment surface based on the data. Considering that the received data may contain defects, it is necessary to filter the received data before performing defect detection based on the received data. That is, in some embodiments, before performing defect detection on the containment surface based on the image data in S16, the following steps are further included:

[0090] Check whether the above data meets the preset quality requirements.

[0091] Correspondingly, the above S16, performing defect detection on the surface of the containment vessel according to the above image data, includes:

[0092] When the above data meets the preset quality requirements, defect detection is performed on the surface of the containment shell based on the above image data.

[0093] Among them, the above-mentioned quality requirements are related to the type of data. For example, when the data is image data, the quality requirements are quality requirements for image data. When the data includes other types of data in addition to image data, the quality requirements include not only quality requirements for image data, but also quality requirements for the other types of data.

[0094] For example, when the data includes image data and flight data of an aircraft, the above-mentioned preset quality requirements include preset image requirements and preset waypoint quantity requirements. At this time, detecting whether the above-mentioned data meets the preset quality requirements includes: detecting the clarity and / or contrast and / or noise level of the above-mentioned image data to see whether they meet the above-mentioned preset image requirements; detecting whether the number of waypoints in the above-mentioned flight data meets the above-mentioned preset waypoint quantity requirements.

[0095] Specifically, for image data, the clarity of the image data is detected to see if it meets the clarity requirements of the preset image requirements, and / or the contrast of the image data is detected to see if it meets the contrast requirements of the preset image requirements, and / or the noise level of the image data is detected to see if it meets the noise level requirements of the preset image requirements. With respect to flight data, since the generated mission route includes information about specific waypoints, and a photographic action is typically performed when the aircraft arrives at a waypoint, the number of images corresponding to the image data can be compared with the total number of waypoints in the mission route. If the difference between the two is greater than a preset difference threshold, it is determined that the number of waypoints in the flight data does not meet the preset waypoint number requirement. Otherwise, it is determined that the number of waypoints in the flight data meets the preset waypoint number requirement.

[0096] In an embodiment of the present application, when it is determined that the received data meets the preset quality requirements, it indicates that the quality of the data is high, and the defect detection results obtained by processing the higher quality data are more accurate. Therefore, when it is determined that the received data meets the preset quality requirements, defect detection is performed on the containment surface based on the image data in the received data, which is beneficial to improving the accuracy of the defect detection results.

[0097] In some embodiments, considering the need to stitch images taken by the aircraft on the same mission route, and the prerequisite for successful stitching is that the two images have a certain degree of overlap, it is necessary to determine the degree of overlap before performing defect detection. That is, when the above data meets the preset quality requirements, defect detection of the containment surface based on the above image data includes:

[0098] When the above data meets the preset quality requirements, it is detected whether the spatial overlap of the image data taken by the aircraft at adjacent waypoints is greater than the preset value. If it is greater than the preset value, the defect detection of the above containment surface is performed based on the above image data.

[0099] Specifically, the system checks whether the degree of geographic overlap between two images captured by the aircraft at any two adjacent waypoints along the same mission route exceeds a preset value. If both values ​​are greater than the preset value, the images captured along the mission route can be stitched together into a complete image. A complete image reduces the probability of missing information about the inspection area, which in turn helps improve the accuracy of defect detection results when performing defect detection on the containment surface corresponding to the inspection area based on this complete image.

[0100] In the embodiment of the present application, since the annular corridor is divided into multiple detection areas in advance, and corresponding mission routes are set for the divided detection areas, when the image data (or images) taken for each mission route are spliced ​​into corresponding spliced ​​images, it is equivalent to obtaining an image of the entire containment surface of the annular corridor. Afterwards, defect analysis is performed on these spliced ​​images (or images of the entire containment surface) to obtain defect detection results on the containment surface.

[0101] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0102] The above describes the defect detection method for a nuclear power building provided in an embodiment of the present application from the perspective of a ground station. The following further describes the defect detection method for a nuclear power building in conjunction with a defect detection system for a nuclear power building.

[0103] Figure 2 A structural block diagram of a defect detection system for a nuclear power building provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0104] exist Figure 2In the embodiment, the defect detection system 2 for a nuclear power building includes: a point cloud data acquisition device 21, a ground station 22, and an aircraft 23. The structure of the nuclear power building includes a double-layer containment structure, and a ring corridor is formed in the middle of the double-layer containment structure.

[0105] The point cloud data acquisition device 21 is used to acquire three-dimensional data of the annular corridor to obtain three-dimensional point cloud data of the annular corridor.

[0106] The point cloud data acquisition device 21 here can be a three-dimensional laser scanner, a depth camera, a binocular vision, etc., which is not limited here.

[0107] The 3D point cloud data for the annular corridor includes location information corresponding to sampling points on the outer surface of the inner shell, the inner surface of the outer shell, obstacles between the inner and outer shells, and other surfaces. This 3D point cloud data may also include color information, reflectivity, etc. Optionally, to improve the accuracy of the acquired 3D point cloud data, the 3D point cloud data for the annular corridor may be acquired after the nuclear power building is determined to have no defects. For example, 3D data collection for the annular corridor may be performed after the nuclear power building has been inspected and accepted.

[0108] The above-mentioned ground station 22 is used to obtain the three-dimensional point cloud data of the above-mentioned annular corridor, construct a three-dimensional point cloud model of the above-mentioned annular corridor based on the above-mentioned three-dimensional point cloud data, generate a mission route based on the above-mentioned three-dimensional point cloud model, and send the above-mentioned mission route to the aircraft, wherein the propeller and / or fan blades of the above-mentioned aircraft are installed inside the duct.

[0109] The specific processing process of the ground station 22 is the same as that of the ground station in the above embodiment, and will not be repeated here.

[0110] The above-mentioned aircraft 23 is used to perform the close flight mission according to the received above-mentioned mission route, photograph the containment surface of the above-mentioned annular corridor, obtain image data, and send data including the above-mentioned image data to the above-mentioned ground station.

[0111] The aircraft 23 here refers to a device that can fly in the air, including drones and rotorcraft.

[0112] Optionally, the aircraft 23 may be a dual-ducted UAV. The frame structure of the dual-ducted UAV is as follows: Figure 3As shown, it adopts a double-ducted aerodynamic layout structure. Considering the characteristics of carbon fiber composite materials with light weight and high strength, the double-ducted UAV can be made of carbon fiber composite materials. The double-ducted UAV has large lift, high load, and the propeller is well protected by the ducted tube, so it can fly safely close to buildings. Optionally, the ducted engine wheelbase of the double-ducted UAV can be 320mm, weighing 2.2kg (including battery), fully loaded for 22 minutes, and the positioning accuracy is less than 5cm. Its positioning and autonomous flight functions are achieved by carrying an inertial measurement unit (IMU) inertial navigation unit, a laser sensor, a magnetometer, a binocular camera and a Raspberry Pi 4B (Raspberry Pi 4 Model B) microprocessor, among which the Raspberry Pi 4B is a powerful single-board computer.

[0113] Optionally, in addition to sending image data to the ground station, the aircraft 23 may also send its own flight data to the ground station. This flight data may include information about waypoints along the mission route and data from the aircraft 23's sensors, such as linear acceleration information and angular velocity information of the aircraft 23, which are not limited here.

[0114] The ground station 22 is also used to receive data sent by the aircraft 23 and perform defect detection on the surface of the containment vessel based on the image data.

[0115] In the embodiment of the present application, since a three-dimensional point cloud model of the annular corridor can be constructed based on the three-dimensional point cloud data of the annular corridor collected by the point cloud data acquisition device, a corresponding mission route can be generated based on the three-dimensional point cloud model. Therefore, after the aircraft obtains data including image data of the containment surface according to the mission route, defect detection of the containment surface can be performed based on the image data taken by the aircraft. Since there is no need to set up a scaffolding platform when performing defect detection on the containment surface, and there is no need for manual close-range detection of the containment surface, the detection efficiency is improved and the safety risks faced by people are reduced. In addition, since the propeller and / or fan blades of the aircraft are installed inside the duct, even if the aircraft flies in the annular corridor, its propeller and / or fan blades will not directly cause damage to the containment surface.

[0116] In some embodiments, the defect detection system 2 for a nuclear power building further includes a positioning target. The aircraft 23 is equipped with a binocular vision system, which detects the positioning target using the binocular vision system to achieve a sensing and positioning function. The annular corridor is divided into multiple detection areas, and each detection area is provided with at least one positioning target. Before photographing the containment surface in the annular corridor, the aircraft 23 is further configured to:

[0117] When the binocular vision system of the above-mentioned aircraft 23 detects the above-mentioned positioning target, the coordinate information of the above-mentioned positioning target in the point cloud coordinate system is obtained, and the coordinate information of the above-mentioned positioning target in the aircraft coordinate system is determined, and the coordinate system is aligned according to the coordinate information of the above-mentioned positioning target in the point cloud coordinate system and the coordinate information in the aircraft coordinate system, and the coordinate information of the above-mentioned aircraft 23 in the above-mentioned point cloud coordinate system is determined according to the result of the coordinate system alignment, wherein the above-mentioned point cloud coordinate system is a coordinate system constructed based on the above-mentioned nuclear power building, and the above-mentioned aircraft coordinate system is a coordinate system constructed based on the above-mentioned aircraft 23.

[0118] Among them, the binocular vision system here is a computer vision technology that simulates human binocular vision. It uses two cameras to capture images of the same scene from different angles and uses the principle of parallax to calculate the three-dimensional position information of objects in the scene.

[0119] When the aircraft 23 detects the positioning target through the binocular vision system, the parallax principle can be used to calculate the coordinate information of the positioning target in the aircraft coordinate system, and the image of the positioning target can be analyzed to obtain the coordinate information of the positioning target in the point cloud coordinate system (for example, when the positioning target contains a pattern for indicating coordinate information, the corresponding coordinate information is obtained by analyzing the pattern). The coordinate information of the same positioning target in the point cloud coordinate system is compared with the coordinate information in the aircraft coordinate system, and the point cloud coordinate system and the aircraft coordinate system are aligned according to the comparison result to obtain the alignment result. The coordinate information of the aircraft in the point cloud coordinate system is converted according to the alignment result of the point cloud coordinate system and the aircraft coordinate system.

[0120] In the embodiment of the present application, since the aircraft first aligns the coordinate system and then photographs the containment surface of the annular corridor, the coordinate information of the aircraft in the point cloud coordinate system can be determined to estimate the detection area corresponding to the image data currently photographed.

[0121] In some embodiments, before obtaining the coordinate information of the positioning target in the point cloud coordinate system, the aircraft 23 is further used to:

[0122] When the binocular vision system of the above-mentioned aircraft 23 detects the above-mentioned positioning target, a positioning accuracy self-checking program is executed based on the above-mentioned positioning target; after the above-mentioned positioning accuracy self-checking program is completed, the positioning accuracy of the above-mentioned aircraft 23 is evaluated.

[0123] Specifically, a preset positioning accuracy self-checking program is executed with the positioning target as a reference benchmark. The self-checking action of the positioning accuracy self-checking program is used to control the aircraft 23 to first change its current position and then restore it, and / or first change its current angle and then restore it, and then compare the position information before the self-checking action with the position information after the self-checking action is executed, and / or compare the angle information before the self-checking action with the angle information after the self-checking action is executed, and evaluate the positioning accuracy of the aircraft based on the comparison result. For example, it is assumed that the self-checking action includes: (1) the drone detects and locks the target coordinates using binocular vision; (2) performs an ascent of 1m, a rightward translation of 1m, an in-situ rotation of 180°, a leftward translation of 1m, an in-situ rotation of 540°, and a descent of 1m; (3) the binocular vision detects the target position coordinates again; (4) the software calculates and analyzes the cumulative error of the motion trajectory, such as analyzing the difference in the three-dimensional coordinates and the difference in the yaw angle of the aircraft before and after the self-checking action is executed, obtaining the accuracy of the coordinates based on the difference in the three-dimensional coordinates, obtaining the accuracy of the angle based on the difference in the yaw angle, and evaluating the positioning accuracy based on the accuracy of the coordinates and the accuracy of the angle. Optionally, if the accuracy of the coordinates is less than 3 cm and the accuracy of the angle (or yaw angle) is greater than 0.5°, recheck the status of each sensor of the drone.

[0124] In order to more clearly describe the processing flow of the defect detection system for nuclear power buildings provided by the embodiment of the present application, Figure 4 Provide a description.

[0125] S401: Divide the annular corridor into several detection areas.

[0126] The detection area may be divided according to at least one of the following reference information, including: the position of the buttress structure provided in the annular corridor, the transmission distance of the signal in the annular corridor, the visibility, and the number of layers of the grid platform that divides the annular corridor.

[0127] S402, deploying positioning targets.

[0128] Specifically, the positioning target is pasted or mounted on the wall of the containment vessel to be inspected. For example, when the containment vessel to be inspected is the inner containment vessel, the positioning target is pasted on the surface of the inner containment vessel.

[0129] S403: Collect three-dimensional point cloud data of the circular corridor.

[0130] Specifically, the three-dimensional point cloud data of the circular corridor is collected by point cloud data collection equipment.

[0131] S404: Establish a three-dimensional point cloud model and determine the point cloud coordinate system.

[0132] The three-dimensional point cloud data of each detection area are spliced ​​to obtain a corresponding three-dimensional point cloud model. The coordinate system of the three-dimensional point cloud model is the coordinate system constructed based on the nuclear power building.

[0133] S405 , generating a mission route based on the three-dimensional point cloud model and the positioning target, and sending the mission route to the aircraft.

[0134] Specifically, the positioning target in the detection area can be used as the starting point of the mission route. The waypoints of the mission route are generated in a certain order (for example, from left to right when the positioning target is on the leftmost side). Each waypoint constitutes the corresponding mission route. After the mission route is generated by the ground station, it is sent to the aircraft.

[0135] S406, the aircraft performs a positioning accuracy self-check procedure.

[0136] After receiving the flight mission, the aircraft performs a positioning accuracy self-check procedure to determine whether its accuracy meets the requirements.

[0137] S407, aligning the point cloud coordinate system and the aircraft coordinate system.

[0138] When the accuracy of the aircraft meets the requirements, the coordinate system where it is located (i.e., the aircraft coordinate system) is aligned with the point cloud coordinate system to obtain the coordinate information of the aircraft in the point cloud coordinate system.

[0139] S408 , while the aircraft is flying according to the mission route, its flight trajectory is monitored in real time.

[0140] The ground station monitors whether the flight trajectory of the aircraft matches the mission route based on the real-time coordinate information of the aircraft in the point cloud coordinate system.

[0141] S409, image processing and defect detection.

[0142] The ground station receives data including image data sent by the aircraft, processes an image corresponding to the image data, and identifies whether there are defects on the containment surface in the image.

[0143] After the aircraft sends the data of one inspection area to the ground station, it continues to perform the next flight mission to realize defect detection in the next inspection area.

[0144] Corresponding to the defect detection method for nuclear power buildings described in the above embodiment, Figure 5 A structural block diagram of a defect detection device for a nuclear power building provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0145] Reference Figure 5The nuclear power building defect detection device 5 includes a double-layer containment structure with a circular corridor formed in the middle of the double-layer containment structure. The nuclear power building defect detection device 5 includes: a 3D point cloud data acquisition module 51, a 3D point cloud model construction module 52, a mission route generation module 53, a mission route sending module 54, a data receiving module 55, and a defect detection module 56. Among them:

[0146] The three-dimensional point cloud data acquisition module 51 is used to acquire the three-dimensional point cloud data of the annular corridor.

[0147] The three-dimensional point cloud model construction module 52 is used to construct a three-dimensional point cloud model of the above-mentioned annular corridor based on the above-mentioned three-dimensional point cloud data.

[0148] The mission route generation module 53 is used to generate a mission route according to the above three-dimensional point cloud model.

[0149] The mission route sending module 54 is used to send the above mission route to the aircraft so that the above aircraft performs the close flight mission according to the above mission route, wherein the propeller and / or fan blades of the above aircraft are installed inside the duct.

[0150] The data receiving module 55 is used to receive data sent by the above-mentioned aircraft, and the above-mentioned data includes image data obtained by the above-mentioned aircraft photographing the surface of the containment shell of the above-mentioned annular corridor.

[0151] The defect detection module 56 is used to perform defect detection on the surface of the containment vessel according to the image data.

[0152] In the embodiment of the present application, since a three-dimensional point cloud model of the annular corridor is constructed, a corresponding mission route can be generated based on the three-dimensional point cloud model. Therefore, after the aircraft obtains data including image data of the containment surface according to the mission route, defect detection of the containment surface can be performed based on the image data taken by the aircraft. Since there is no need to set up a scaffolding platform when performing defect detection on the containment surface, and there is no need for manual close-range detection of the containment surface, the detection efficiency is improved and the safety risks faced by people are reduced. In addition, since the propeller and / or fan blades of the aircraft are installed inside the duct, even if the aircraft flies in the annular corridor, its propeller and / or fan blades will not directly cause damage to the containment surface.

[0153] In some embodiments, the three-dimensional point cloud data acquisition module 51 is specifically used to:

[0154] The annular corridor is divided into a plurality of detection areas, and three-dimensional point cloud data of each of the detection areas is acquired to obtain three-dimensional point cloud data of the annular corridor, wherein each of the detection areas is provided with at least one positioning target.

[0155] Correspondingly, the mission route generation module 53 is specifically used to:

[0156] The mission route is generated based on the positioning targets of the detection area in the three-dimensional point cloud model.

[0157] In some embodiments, the three-dimensional point cloud data acquisition module 51 is specifically used to:

[0158] The annular corridor is divided into a plurality of detection areas according to at least one of the following reference information, wherein the reference information includes: the position of the buttress structure provided in the annular corridor, the transmission distance of the signal in the annular corridor, the visibility, and the number of layers divided by the grid platform into which the annular corridor is divided.

[0159] In some embodiments, when generating the mission route according to the positioning targets of the detection area in the three-dimensional point cloud model, the mission route generation module 53 is specifically configured to:

[0160] The positioning target of the above-mentioned detection area in the above-mentioned three-dimensional point cloud model is determined as the starting point of the mission route; the above-mentioned mission route is generated based on the starting point of the above-mentioned mission route and the following conditions, the above-mentioned conditions include: the generated above-mentioned mission route avoids obstacles in the above-mentioned circular corridor, the spatial overlap of image data obtained by the above-mentioned aircraft at adjacent waypoints is greater than a preset value, and the distance between the above-mentioned aircraft and the above-mentioned containment surface is within a preset distance range.

[0161] In some embodiments, the defect detection device 5 for a nuclear power building further includes:

[0162] The quality requirement compliance judgment module is used to detect whether the above data meets the preset quality requirements before performing defect detection on the above containment shell surface based on the above image data.

[0163] Correspondingly, the defect detection module 56 is specifically configured to:

[0164] When the above data meets the preset quality requirements, defect detection is performed on the surface of the containment shell based on the above image data.

[0165] In some embodiments, when the data meets the preset quality requirements, performing defect detection on the surface of the containment vessel based on the image data includes:

[0166] When the above data meets the preset quality requirements, it is detected whether the spatial overlap of the image data taken by the aircraft at adjacent waypoints is greater than the preset value. If it is greater than the preset value, the defect detection of the above containment surface is performed based on the above image data.

[0167] In some embodiments, the data includes image data and flight data of the aircraft, the preset quality requirements include preset image requirements and preset waypoint quantity requirements, and whether the quality requirements are met by the judgment module includes:

[0168] The image data quality judgment unit is used to detect whether the clarity and / or contrast and / or noise level of the above image data meet the above preset image requirements.

[0169] The flight data quality judgment unit is used to detect whether the number of waypoints in the above-mentioned flight data meets the above-mentioned preset waypoint quantity requirement.

[0170] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0171] Figure 6 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present application. Figure 6 As shown, the electronic device 6 of this embodiment includes: at least one processor 60 ( Figure 6 Only one processor is shown in the figure), a memory 61, and a computer program 62 stored in the memory 61 and executable on the at least one processor 60, wherein the processor 60 implements the steps of any of the above-mentioned method embodiments when executing the computer program 62.

[0172] The electronic device 6 can be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device can include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that Figure 6 This is merely an example of the electronic device 6 and does not constitute a limitation on the electronic device 6 . The electronic device 6 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 6 may also include input and output devices, network access devices, etc.

[0173] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0174] In some embodiments, the memory 61 may be an internal storage unit of the electronic device 6, such as a hard disk or memory of the electronic device 6. In other embodiments, the memory 61 may also be an external storage device of the electronic device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 6. Furthermore, the memory 61 may also include both an internal storage unit of the electronic device 6 and an external storage device. The memory 61 is used to store an operating system, an application program, a boot loader, data, and other programs, such as the program code of the computer program. The memory 61 may also be used to temporarily store data that has been output or is about to be output.

[0175] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0176] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0177] An embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device can implement the steps of the above-mentioned method embodiments when executing the computer program product.

[0178] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / electronic device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0179] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0180] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0181] In the embodiments provided in this application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0182] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0183] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for detecting defects in nuclear power buildings, characterized in that: The structure of the nuclear power building includes a double-layer containment structure, wherein an annular corridor is formed in the middle of the double-layer containment structure. The defect detection method of the nuclear power building includes: Acquiring three-dimensional point cloud data of the annular corridor; Constructing a three-dimensional point cloud model of the annular corridor according to the three-dimensional point cloud data; generating a mission route according to the three-dimensional point cloud model; sending the mission route to an aircraft so that the aircraft performs a close-flight mission according to the mission route, wherein a propeller and / or fan blade of the aircraft is installed inside a duct; receiving data sent by the aircraft, the data including image data obtained by the aircraft photographing the containment surface of the annular corridor; Defect detection is performed on the surface of the containment vessel according to the image data.

2. The method for detecting defects in a nuclear power building according to claim 1, wherein: The obtaining of the three-dimensional point cloud data of the annular corridor includes: Dividing the annular corridor into a plurality of detection areas, acquiring three-dimensional point cloud data of each of the detection areas, and obtaining three-dimensional point cloud data of the annular corridor, wherein each of the detection areas is provided with at least one positioning target; Generating a mission route according to the three-dimensional point cloud model includes: The mission route is generated according to the positioning target of the detection area in the three-dimensional point cloud model.

3. The method for detecting defects in a nuclear power building according to claim 2, wherein: The annular corridor is divided into a plurality of detection areas, including: The annular corridor is divided into multiple detection areas based on at least one of the following reference information, wherein the reference information includes: the position of the buttress structure set in the annular corridor, the transmission distance of the signal in the annular corridor, the visibility and the number of layers of the grid platform that divides the annular corridor.

4. The method for detecting defects in a nuclear power building according to claim 2, wherein: Generating the mission route according to the positioning target of the detection area in the three-dimensional point cloud model includes: Determine the positioning target of the detection area in the three-dimensional point cloud model as the starting point of the mission route; The mission route is generated based on the starting point of the mission route and the following conditions, wherein the conditions include: the generated mission route avoids obstacles in the annular corridor, the spatial overlap of image data captured by the aircraft at adjacent waypoints is greater than a preset value, and the distance between the aircraft and the containment surface is within a preset distance range.

5. The method for detecting defects in a nuclear power building according to any one of claims 1 to 4, characterized in that: Before performing defect detection on the containment surface according to the image data, the method further includes: Checking whether the data meets the preset quality requirements; The performing defect detection on the containment surface according to the image data includes: When the data meets the preset quality requirements, defect detection is performed on the surface of the containment shell according to the image data.

6. The method for detecting defects in a nuclear power building according to claim 5, wherein: When the data meets the preset quality requirements, performing defect detection on the containment surface according to the image data includes: When the data meets the preset quality requirements, it is detected whether the spatial overlap of the image data taken by the aircraft at adjacent waypoints is greater than a preset value. If it is greater than the preset value, defect detection is performed on the containment surface based on the image data.

7. The method for detecting defects in a nuclear power building according to claim 5, wherein: The data includes image data and flight data of the aircraft, the preset quality requirements include preset image requirements and preset waypoint quantity requirements, and detecting whether the data meets the preset quality requirements includes: detecting whether the clarity and / or contrast and / or noise level of the image data meet the preset image requirements; Check whether the number of waypoints in the flight data meets the preset waypoint number requirement.

8. A defect detection system for a nuclear power building, characterized in that: The structure of the nuclear power building includes a double-layer containment structure, and a ring corridor is formed in the middle of the double-layer containment structure. The defect detection system of the nuclear power building includes: point cloud data acquisition equipment, a ground station and an aircraft; The point cloud data acquisition device is used to collect three-dimensional data of the annular corridor to obtain three-dimensional point cloud data of the annular corridor; The ground station is configured to acquire three-dimensional point cloud data of the annular corridor, construct a three-dimensional point cloud model of the annular corridor based on the three-dimensional point cloud data, generate a mission route based on the three-dimensional point cloud model, and transmit the mission route to an aircraft, wherein a propeller and / or fan blade of the aircraft is installed inside the duct; The aircraft is configured to perform a close flight mission according to the received mission route, photograph the containment surface of the annular corridor, obtain image data, and transmit data including the image data to the ground station; The ground station is further configured to receive data sent by the aircraft and perform defect detection on the containment surface based on the image data.

9. The defect detection system for a nuclear power building according to claim 8, characterized in that: The annular corridor is divided into a plurality of detection areas, and each detection area is provided with at least one positioning target. Before photographing the containment surface of the annular corridor, the aircraft is further used to: When the binocular vision system of the aircraft detects the positioning target, the coordinate information of the positioning target in the point cloud coordinate system is obtained, and the coordinate information of the positioning target in the aircraft coordinate system is determined. The coordinate systems are aligned according to the coordinate information of the positioning target in the point cloud coordinate system and the coordinate information in the aircraft coordinate system. The coordinate information of the aircraft in the point cloud coordinate system is determined according to the result of the coordinate system alignment, wherein the point cloud coordinate system is a coordinate system constructed based on the nuclear power building, and the aircraft coordinate system is a coordinate system constructed based on the aircraft.

10. The defect detection system for a nuclear power building according to claim 9, characterized in that: Before acquiring the coordinate information of the positioning target in the point cloud coordinate system, the aircraft is further used to: When the binocular vision system of the aircraft detects the positioning target, a positioning accuracy self-checking program is performed based on the positioning target; After the positioning accuracy self-checking program is completed, the positioning accuracy of the aircraft is evaluated.

11. A defect detection device for a nuclear power building, characterized in that: The structure of the nuclear power building includes a double-layer containment structure, wherein an annular corridor is formed in the middle of the double-layer containment structure. The defect detection device of the nuclear power building includes: A three-dimensional point cloud data acquisition module, used to acquire three-dimensional point cloud data of the annular corridor; A three-dimensional point cloud model construction module, configured to construct a three-dimensional point cloud model of the annular corridor based on the three-dimensional point cloud data; A mission route generation module, configured to generate a mission route based on the three-dimensional point cloud model; a mission route sending module, configured to send the mission route to an aircraft, so that the aircraft performs a close flight mission according to the mission route, wherein the propeller and / or fan blades of the aircraft are installed inside the duct; a data receiving module, configured to receive data sent by the aircraft, wherein the data includes image data obtained by the aircraft photographing the surface of the containment vessel of the annular corridor; A defect detection module is used to perform defect detection on the surface of the containment shell according to the image data.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

13. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

14. A computer program product, characterized in that The invention comprises a computer program, which, when executed, causes the method according to any one of claims 1 to 7 to be performed.

Images