Methods, systems, devices, and storage media for testing of spacecraft tubing welds

Abstract

The application discloses a kind of for spacecraft pipeline weld test method, system, equipment and storage medium, the method comprises: parameter calibration processing is carried out to visual sensor, robot and leak rate detection tool in detection device respectively, and calibration result is obtained;The point cloud data of the surrounding environment of the spacecraft structure surface obtained is handled, and spacecraft structure model file is obtained;Image of spacecraft region to be detected is acquired, and the relative pose relationship between robot coordinate system and spacecraft model coordinate system is established;The target position information of all welds to be detected in spacecraft region to be detected and pipeline clamping attitude information are determined;Based on target position information and attitude information, spacecraft structure model file, relative pose relationship, the detection path planning and leak rate test of weld to be detected are carried out, and leak rate test result is determined.The scheme can realize the flexible and intelligent test of spacecraft assembly process pipeline system weld leak rate, and effectively improves the spacecraft development efficiency.

Description

Technical Field

[0001] This invention generally relates to the field of spacecraft assembly and testing technology, and specifically to a testing method, system, equipment, and storage medium for spacecraft pipeline welds. Background Technology

[0002] With the rapid development of satellite communication technology, spacecraft piping systems have attracted much attention as crucial components of spacecraft operation. These systems include propulsion, thermal control, and environmental and life support systems. Propulsion piping transports fuel, oxidizers, and other working fluids for the propulsion system. Thermal control piping, composed of active and passive heat pipes, is responsible for temperature control. The environmental and life support system regulates the internal gas environment, ensuring suitable cabin gas composition and pressure. The sealing performance of a spacecraft is a critical parameter for measuring its on-orbit lifespan. Leaks in manned spacecraft can endanger astronauts' lives, and severe leaks may even lead to explosions. Therefore, rigorous sealing performance testing during spacecraft development is essential to ensure safe and normal operation.

[0003] Currently, leak rate testing of spacecraft piping systems primarily involves confirming whether the leak rates of individual welds, bolt connections, and the overall system leak rate meet the required specifications. The leak rates of individual welds and bolt connections are tested using a helium mass spectrometry (HMS) leak detector, while the overall system leak rate is tested using either vacuum HMS or atmospheric pressure HMS leak detection. However, current weld leak rate testing relies entirely on manual operation. As the number of spacecraft developed increases and the development cycle shortens, a significant amount of manpower is required for testing, resulting in substantial labor costs and low spacecraft development efficiency. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a testing method, system, device and storage medium for spacecraft pipeline welds.

[0005] In a first aspect, the present invention provides a testing method for welded seams in spacecraft piping, the method comprising:

[0006] The parameters of the vision sensor, robot, and leak rate detection tool in the detection device were calibrated to obtain the calibration results.

[0007] The acquired point cloud data of the spacecraft structure surface and the surrounding environment are processed to obtain the spacecraft structure model file;

[0008] Acquire images of the area to be inspected on the spacecraft, and establish the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system based on the calibration results;

[0009] Based on the image of the spacecraft's inspection area, determine the target location information and pipeline clamping attitude information of all welds to be inspected in the spacecraft's inspection area;

[0010] Based on the target position information, the attitude information, the spacecraft structural model file, and the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, the detection path is planned and the leak rate is tested for the weld to be inspected, and the leak rate test results of all welds to be inspected in the spacecraft inspection area are obtained.

[0011] In one embodiment, based on the target position and attitude information, the spacecraft structural model file, and the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, a detection path is planned and a leak rate test is performed on the weld to be inspected, obtaining the leak rate test results for all welds to be inspected in the spacecraft's inspection area, including:

[0012] Based on the spacecraft surface point cloud data and the surrounding environment point cloud data, a planar feature algorithm is used to identify the pipeline base plate planar point cloud data, and a planar feature fitting algorithm is used to determine the pipeline base plate planar normal vector information based on the pipeline base plate planar point cloud data.

[0013] Based on the normal vector information of the pipeline base plate plane, the leak rate detection tool is adjusted to its initial attitude information; the initial attitude information is used to characterize that the leak rate detection tool is perpendicular to the pipeline base plate plane;

[0014] Based on the spacecraft structural model file, the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, the target position information of the weld to be inspected, and the attitude information, a motion path for inspecting the weld to be inspected is planned.

[0015] Based on the motion path, a leak rate test is performed on the weld to be tested, and the leak rate test results of all welds to be tested in the spacecraft's testing area are obtained.

[0016] In one embodiment, based on the motion path, a leak rate test is performed on the weld to be inspected to obtain the leak rate test results of all welds to be inspected in the spacecraft's inspection area, including:

[0017] The current weld to be inspected is determined according to the weld inspection order from shortest to longest according to the motion path, and the specified operation is executed cyclically until all welds to be inspected have been inspected.

[0018] The specified operation includes:

[0019] For the current weld to be inspected, based on the motion path, the robot controls the leak rate detection tool to move to a position directly above the current weld to be inspected;

[0020] The image of the weld seam to be inspected is acquired by a local vision sensor in the vision sensor.

[0021] Based on the image of the weld to be inspected, determine the center position information and pipeline routing information of the weld to be inspected.

[0022] Based on the center position information and pipeline routing information of the current weld to be inspected, a leak rate test is performed on the current weld to be inspected to obtain the leak rate test result corresponding to the current weld to be inspected.

[0023] Determine whether the current weld to be inspected is the last weld to be inspected among all welds to be inspected;

[0024] If the weld is not the last one to be inspected, the control proceeds to the next specified operation; if the weld is the last one to be inspected, the control does not proceed to the next specified operation.

[0025] In one embodiment, based on the center position information and pipeline routing information of the current weld to be inspected, a leak rate test is performed on the current weld to be inspected to obtain the leak rate test result corresponding to the current weld to be inspected, including:

[0026] Based on the center position information of the current weld to be inspected and the pipeline routing information, the initial posture information of the leak rate detection tool is adjusted to the target posture information; the target posture information is used to characterize the leak rate detection tool clamping the current weld to be inspected.

[0027] The leak rate detection tool is used to clamp and cover the weld seam to be inspected to form a sealed space.

[0028] The concentration of the leaking gas in the weld to be inspected is detected by evacuation, and the leak rate test result corresponding to the weld to be inspected is obtained.

[0029] In one embodiment, based on an image of the spacecraft's inspection area, the target location information of all welds to be inspected within the inspection area is determined, including:

[0030] The image of the spacecraft's target area is acquired by the large field-of-view vision sensor in the vision sensor;

[0031] The trained weld recognition model is used to process the image of the spacecraft's inspection area to identify all the welds to be detected in the image of the spacecraft's inspection area.

[0032] Determine the target location information of the weld to be inspected.

[0033] In one embodiment, the calibration result includes a first relative pose relationship between the visual sensor coordinate system and the robot coordinate system, and a second relative pose relationship between the robot coordinate system and the leak rate detection tool coordinate system;

[0034] The parameters of the vision sensor, robot, and leak rate detection tool in the detection device were calibrated separately to obtain calibration results, including:

[0035] Select a visual calibration plate based on the field of view parameters of the visual sensor;

[0036] Determine the attribute parameters of the large field-of-view visual sensor and the local visual sensor in the visual sensor, and the first relative orientation relationship between the large field-of-view visual sensor and the local visual sensor;

[0037] Determine the second relative orientation relationship between the large field-of-view vision sensor coordinate system and the local vision sensor coordinate system;

[0038] Based on the first relative orientation relationship and the second relative orientation relationship, the large field-of-view visual sensor coordinate system is set as the visual sensor coordinate system;

[0039] Based on the vision calibration board, a first relative pose relationship between the vision sensor coordinate system and the robot coordinate system is determined, and a second relative pose relationship between the robot coordinate system and the leak rate detection tool coordinate system is determined.

[0040] In one embodiment, establishing the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system includes:

[0041] Based on the first relative pose relationship and the second relative pose relationship, a binocular stereo matching algorithm is used to determine the three-dimensional point cloud data of the area to be detected in the robot coordinate system, and the three-dimensional point cloud data is used as the orientation data;

[0042] The point cloud data of the spacecraft's structural surface and the point cloud data of the surrounding environment are used as the target source data.

[0043] A 3D point cloud registration algorithm is used to register the data to be oriented acquired by the vision sensor and the target source data to determine the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system.

[0044] Secondly, embodiments of this application provide a testing system for spacecraft pipeline welds. The system includes: a spacecraft pipeline to be tested and a testing device. The testing device includes a transfer platform, a robot, a vehicle-mounted workstation, a rotary lifting mechanism, a force sensor, a leak rate detection tool, and a vision sensor.

[0045] The transfer platform is equipped with the vehicle-mounted workstation and the rotating lifting mechanism; the robot is connected to the rotating lifting mechanism, the force sensor, the leak detection tool, and the vision sensor respectively; the vehicle-mounted workstation is electrically connected to the transfer platform, the robot, the rotating lifting mechanism, the force sensor, the leak detection tool, and the vision sensor respectively.

[0046] Thirdly, embodiments of this application provide a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the testing method for spacecraft pipeline welds as described in the first aspect above.

[0047] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon for implementing the testing method for spacecraft pipeline welds as described in the first aspect above.

[0048] The testing method, system, equipment, and storage medium for spacecraft pipeline welds provided in this application embodiment calibrates the parameters of the vision sensor, robot, and leak rate detection tool in the testing device to obtain calibration results. It then processes the acquired point cloud data of the spacecraft structure surface and the surrounding environment to obtain a spacecraft structure model file. Next, it acquires an image of the area to be tested on the spacecraft and establishes the target relative pose relationship between the robot coordinate system and the spacecraft model coordinate system based on the calibration results. Based on the image of the area to be tested, it determines the target position information and pipeline clamping attitude information of all welds to be tested in the area. Finally, based on the target position and attitude information, the spacecraft structure model file, and the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, it performs detection path planning and leak rate testing on the welds to be tested, obtaining the leak rate test results for all welds to be tested in the area. Compared with existing technologies, this technical solution does not rely on manual operation. By calibrating the parameters of the vision sensors, robots, and leak detection tools in the detection device, and by constructing a spacecraft structural model file, it provides data guidance for the subsequent detection device to accurately detect weld leak rates. Based on the image of the area to be inspected on the spacecraft, it can accurately determine the target location information and pipeline routing information of all welds to be inspected. This combines more comprehensive information to conduct leak rate testing on the welds to be inspected, realizing flexible, intelligent, and autonomous testing of welding leak rates in the pipeline system during the spacecraft assembly process. This further effectively improves the development efficiency and automation level of large spacecraft. Attached Figure Description

[0049] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0050] Figure 1 A schematic diagram of the structure of a testing system for spacecraft pipeline welds provided in an embodiment of this application;

[0051] Figure 2 A schematic diagram of the structure of a testing system for spacecraft pipeline welds provided in an embodiment of this application;

[0052] Figure 3 A schematic flowchart illustrating a testing method for spacecraft pipeline welds provided in an embodiment of this application;

[0053] Figure 4 A schematic flowchart of a testing method for spacecraft pipeline welds provided in another embodiment of this application;

[0054] Figure 5 This is a schematic diagram of the system coordinate system calibration provided in the embodiments of this application;

[0055] Figure 6 A schematic flowchart illustrating a testing method for spacecraft pipeline welds provided in an embodiment of this application;

[0056] Figure 7 A schematic flowchart illustrating a testing method for spacecraft pipeline welds provided in an embodiment of this application;

[0057] Figure 8 A schematic diagram of the structure of a testing device for spacecraft pipeline welds provided in an embodiment of this application;

[0058] Figure 9 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0059] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0060] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The present application will now be described in detail with reference to the accompanying drawings and embodiments. The following is an explanation of the relevant terms used in this application:

[0061] Target position information refers to the position information corresponding to the center of all welds to be inspected in the spacecraft inspection area; target attitude information refers to the direction information of the pipeline where the weld to be inspected is located and the normal information of the pipeline base plate; spacecraft structural model refers to the three-dimensional model file obtained by processing the point cloud data of the spacecraft structural surface and the point cloud data of the surrounding environment; pipeline clamping attitude information refers to the attitude information corresponding to the spacecraft pipeline clamping state of the leak rate detection tool.

[0062] As we understand it, a spacecraft is a flight vehicle that performs specific missions such as exploring, developing, and utilizing space and celestial bodies beyond Earth. The spacecraft piping system mainly includes propulsion, thermal control, and environmental control / life support piping. Propulsion piping is responsible for transporting fuel, oxidizer, and other working fluids for the propulsion system; thermal control piping consists of active and passive heat pipes, responsible for temperature control of the spacecraft; and environmental control / life support piping is used to regulate the internal gas environment of the spacecraft, ensuring suitable cabin gas composition and pressure. Even minor leaks in the piping system can reduce the spacecraft's lifespan, while severe leaks can cause explosions. In manned spacecraft, leaks can endanger the lives of astronauts. Therefore, leak testing of the spacecraft piping system is a crucial step in the spacecraft development process. The sealing performance of the piping system needs to be tested during the single-unit stage, the final assembly stage, and before and after mechanical and thermal tests.

[0063] A typical spacecraft piping system mainly consists of individual components such as tanks, gas cylinders, valves, and pipes. During the final assembly stage, these individual components are connected into a closed and complete piping system through welding or bolting. Piping system leak rate testing primarily confirms whether the leak rates of individual welds, bolted joints, and the overall system leak rate meet the required specifications. Currently, weld and bolted joint leak rate testing uses a helium mass spectrometry (HMS) leak detection method, while overall leak rate testing uses either vacuum HMS or atmospheric pressure HMS leak detection. The method for testing pipeline weld leak rate using the HMS leak detection method is as follows: First, the piping system is filled with helium at a specified pressure. Then, all welds are covered with open rubber rings or medical tape. Next, the medical needle at the tip of the suction gun is inserted into the covered area to extract the leaking helium. Finally, based on the proportional relationship between the net reaction value of the tested weld leak and the net reaction value of a standard leak, the leak rate of the tested weld can be calculated.

[0064] As spacecraft functions become increasingly complex, the routing and layout of their piping systems also become more intricate. Taking the Dongfanghong-5 communication platform satellite piping system as an example, this system includes three systems—chemical propulsion, electric propulsion, and thermal control—all requiring leak detection. It comprises 500 welds, 20 bolt connections, and 20 solenoid valves. Currently, all weld leak rate tests rely entirely on manual operation. However, with the increasing number of spacecraft being developed and the shortening development cycle, on-site testing is becoming increasingly demanding. Manual testing incurs significant labor costs, leading to low spacecraft development efficiency.

[0065] In the process of automated testing in industrial manufacturing, the use of industry and its personnel as the carriers of automation, carrying testing equipment for automated testing, has been increasingly applied to equipment such as automobiles, airplanes, and ships. This method is based on the teach-and-play model, requiring fixed test stations, batch testing of test objects with good consistency, and is suitable for pulsed production lines of batch products. However, this testing solution is difficult to adapt to the research and development site of large spacecraft for the following reasons:

[0066] (1) The development of large spacecraft is characterized by multiple types of single-piece designs and requires customized settings. Each spacecraft has a different configuration and the vast majority are produced as single pieces. The automated testing method based on the teaching mode requires a lot of preliminary preparation work in this state, resulting in low testing efficiency.

[0067] (2) The assembly of large spacecraft is characterized by multiple test states, unfixed test stages, unfixed test stations, small operating space, and complex and changeable test environment. Current automated testing methods are difficult to achieve high reliability under complex and changeable conditions.

[0068] (3) There is no prior model data on the distribution of pipeline welds, and the weld distribution is inconsistent between different spacecraft of the same type. The test objectives are unclear and not fixed, which makes it difficult to implement the automated test method of the teaching mode.

[0069] To address the aforementioned shortcomings, this application provides a testing method, system, equipment, and storage medium for spacecraft pipeline welds. Compared to existing technologies, this solution eliminates the need for manual operation. By calibrating the parameters of the visual sensors, robots, and leak detection tools in the testing device, and constructing a spacecraft structural model file, it provides data guidance for subsequent accurate weld leak detection. Based on images of the spacecraft's testing area, it can accurately determine the target location information and pipeline routing information of all welds to be tested, thus combining more comprehensive information to perform leak rate testing on the welds to be tested. This enables flexible, intelligent, and autonomous testing of welding leak rates in the pipeline system during spacecraft assembly, further effectively improving the development efficiency and automation level of large spacecraft.

[0070] Figure 1 This is a schematic diagram of a testing system for spacecraft pipeline welds provided in an embodiment of this application. Figure 1 As shown, the system includes a spacecraft test pipeline 10 and a testing device 20, wherein, please refer to... Figure 2 As shown, the above-mentioned detection device may include: a transfer platform 21, a robot 22, a vehicle-mounted workstation 23, a rotary lifting mechanism 24, a force sensor 25, a leak rate detection tool 26, and a vision sensor 27.

[0071] The aforementioned detection system 20 can be a robotic detection system used to perform leak rate testing on the pipelines to be tested in spacecraft.

[0072] The transfer platform 21 is equipped with a loading workstation 23 and a rotary lifting mechanism 24. The rotary lifting mechanism 24 is connected to a robot 22. The robot 22 is connected to the rotary lifting mechanism 24, a force sensor 25, a leak detection tool 26, and a vision sensor 27.

[0073] The vehicle-mounted workstation 23 is electrically connected to the transfer platform 21, robot 22, rotary lifting mechanism 24, force sensor 25, leak rate detection tool 26 and vision sensor 27 respectively.

[0074] The aforementioned transfer platform 21 is used to carry the detection system to the vicinity of the test pipeline on the spacecraft. The transfer platform can be an AGV transfer platform or other platforms with transfer functions. The transfer platform can include a walking mechanism with the function of moving and walking. It can use Mecanum wheels and support free movement in all directions with a 360° radius without turning. The mobile platform is flexible and suitable for operation in confined spaces.

[0075] Robot 22 is used to control the movement of leak detection tool 26 and vision sensor 27 to perform pipeline weld identification and location and leak rate testing.

[0076] The vehicle-mounted workstation 23 is the control center for the movement of the detection system and the execution of its testing tasks. It controls the transfer platform 21, robot 22, and rotary lifting mechanism 24 to plan their movement paths and execute motions, as well as the force sensor 25, leak detection tool 26, and vision sensor 27 to identify, locate, clamp, and perform leak rate testing on the spacecraft pipeline welds to be inspected. The vehicle-mounted workstation 23 may internally include a processor and memory for controlling the operation of the transfer platform 21, robot 22, rotary lifting mechanism 24, force sensor 25, leak detection tool 26, and vision sensor 27.

[0077] The rotary lifting mechanism 24 is used to drive the robot 22 to rotate and lift.

[0078] Force sensor 25 can be integrated into the end of robot 22 to sense the force on the end of the robot in real time and adjust the clamping force of leak detection tool 26 on the pipeline according to the force to ensure that the robot moves without bumps and that the leak detection tool 26 clamps the pipeline smoothly.

[0079] The leak detection tool 26 may include a mechanical gripper and a helium mass spectrometer leak detector. The mechanical gripper is used to clamp and cover the pipeline weld to form a sealed space. The helium mass spectrometer leak detector is used to detect the concentration of leaking gas in the pipeline weld to be tested, determine the weld leak rate value, and determine whether there is a leak.

[0080] The vision sensor 27 includes a large field-of-view vision sensor and a local vision sensor. The large field-of-view vision sensor is used to identify and coarsely locate the pipe weld within the range of the robot arm length, determine the relative pose relationship between the robot and the spacecraft, and guide the leak rate detection tool 26 to the vicinity of the weld to be inspected. The local vision sensor is used to finely locate the weld to be inspected and determine the pipeline route, and guide the leak rate detection tool 26 to accurately clamp the pipe weld to be inspected.

[0081] For ease of understanding and explanation, the following will use... Figures 3 to 9 This application provides a detailed description of the testing methods, systems, equipment, and storage media for spacecraft pipeline welds provided in its embodiments.

[0082] Figure 3 The diagram shown is a flowchart illustrating a testing method for spacecraft pipeline welds according to an embodiment of this application. This method can be executed by a testing device. Figure 3 As shown, the method includes:

[0083] S101. Perform parameter calibration on the vision sensor, robot, and leak rate detection tool in the detection device to obtain calibration results.

[0084] Understandably, due to the relatively weak structural constraints of the spacecraft and the fact that the test location is not fixed each time, the transfer platform needs to divide the workflow into two stages—test preparation and mission implementation—when it moves to the vicinity of the spacecraft, based on the functional requirements. The first stage, the test preparation stage, involves tasks such as completing the integration and calibration of the testing equipment and the on-site reconstruction of the spacecraft's three-dimensional shape. Then, the second stage, the mission implementation stage, involves tasks such as robot movement planning and approach, relative positioning of the spacecraft and the robot, weld identification and positioning, detection path planning, fine gripping of the grippers, and weld leak rate detection.

[0085] The aforementioned inspection device may include a vision sensor, a robot, a leak detection tool, a rotary lifting mechanism, a force sensor, and a vision sensor. When inspecting welds in a spacecraft piping system using this device, the device must first undergo integrated calibration. This involves calibrating the parameters of the vision sensor, robot, and leak detection tool within the device to obtain calibration results. Leak detection is then performed based on these calibration results.

[0086] The calibration results mentioned above may include a first relative pose relationship between the visual sensor coordinate system and the robot coordinate system, and a second relative pose relationship between the robot coordinate system and the leak rate detection tool coordinate system.

[0087] The visual sensors include a large field-of-view visual sensor and a local visual sensor. The integrated calibration of the detection device includes visual sensor calibration, robot hand-eye calibration, and leak rate detection tool calibration. Visual sensor calibration is used to determine the intrinsic and extrinsic parameters of the large field-of-view and local visual sensors, determine their relative pose relationships, and establish the visual sensor coordinate system. Robot calibration is used to determine the first relative pose relationship between the visual sensor coordinate system and the robot coordinate system. Leak rate detection tool calibration is used to determine the second relative pose relationship between the robot coordinate system and the leak rate detection tool coordinate system.

[0088] In the process of calibrating the parameters of the vision sensor, robot, and leak detection tool in the detection device to obtain calibration results, a vision calibration board can be selected first based on the field-of-view parameters of the vision sensor. Then, the attribute parameters of the large field-of-view vision sensor and the local vision sensor and the first relative orientation relationship between the large field-of-view vision sensor and the local vision sensor can be determined. Then, the second relative orientation relationship between the coordinate system of the large field-of-view vision sensor and the coordinate system of the local vision sensor can be determined. Based on the first and second relative orientation relationships, the coordinate system of the large field-of-view vision sensor is set as the vision sensor coordinate system. Based on the vision calibration board, the first relative pose relationship between the vision sensor coordinate system and the robot coordinate system, and the second relative pose relationship between the robot coordinate system and the leak detection tool coordinate system can be determined.

[0089] Specifically, in the process of visual sensor calibration, a visual calibration board of appropriate size can be selected first based on parameters such as the field of view range and working distance of the large field of view visual sensor and the local visual sensor. Using camera intrinsic parameters and binocular visual calibration algorithms, the camera parameters of the large field of view visual sensor and the local visual sensor, as well as the first relative orientation relationship between the two cameras of the large field of view visual sensor and the local visual sensor, are determined. The large field of view visual sensor and the local visual sensor are then installed and fixed, and both sets of sensors simultaneously take pictures of the same visual calibration board. Using sensor three-dimensional measurement and coordinate system transformation algorithms, the second relative orientation relationship between the coordinate systems of the large field of view visual sensor and the local visual sensor is determined. Then, based on the first relative orientation relationship and the second relative orientation relationship, the coordinate system of the large field of view visual sensor is set as the visual sensor coordinate system.

[0090] During robot calibration, the vision sensor can be first installed and fixed on the robot's end effector, and the robot's coordinate system can be set to the robot's own end flange coordinate system. Then, the robot carries the sensor and takes pictures of the vision calibration board in at least three different poses to obtain the relative orientation relationship between the vision sensor and the vision calibration board under different pose states. Then, the robot hand-eye calibration algorithm is used to determine the relative pose relationship between the vision sensor coordinate system and the robot's end flange coordinate system, thereby determining the first relative pose relationship between the vision sensor coordinate system and the robot coordinate system, and completing the robot hand-eye calibration.

[0091] During the calibration of the leak rate detection tool, the leak rate detection tool calibration fixture can be first installed and fixed on the end effector of the robot, ensuring that the center of the calibration fixture and the needle tip coincides with the center of the gripper hole of the detection tool. The robot end effector coordinate system is set as its own end flange coordinate system, which can also be called the robot coordinate system. The robot carries the detection tool calibration fixture and aligns it with the needle tip of the tool calibration block in four different postures. Then, using the robot end effector calibration algorithm, the second relative pose relationship between the leak rate detection tool coordinate system and the robot coordinate system can be determined, thus completing the calibration of the detection tool.

[0092] In this embodiment, the visual sensor, robot, and leak rate detection tool in the detection device are calibrated to obtain calibration results. These results provide good data guidance for subsequent leak rate testing through the detection device, facilitating more accurate leak rate detection.

[0093] S102. Process the acquired point cloud data of the spacecraft structure surface and the surrounding environment to obtain the spacecraft structure model file.

[0094] It should be noted that the reconstruction of the spacecraft's 3D model involves using large-scale 3D spatial scanning equipment to acquire point cloud data of the spacecraft's structural surface and its surrounding environment, and then reverse-processing this data to obtain the spacecraft structural model file. This spacecraft structural model file is used to assist in the planning of the robot's movement path and to avoid collisions. Because the spacecraft assembly process involves numerous testing states, there may be significant differences between the actual spacecraft and the 3D model. Furthermore, the testing station and surrounding environment are subject to unpredictable factors. Therefore, it is necessary to rely on the reconstruction of the spacecraft's on-site 3D model to obtain prior data, providing a foundation for the robot to automatically plan its movement path and effectively avoid obstacles.

[0095] Specifically, in the process of obtaining the spacecraft structural model file, at least four large-space 3D scanner global target points can be deployed at the spacecraft test site to ensure that the 3D scanner can cover at least three target points at different locations. A large-space 3D scanner is then set up near the spacecraft to scan the structural surface of the area to be tested, global control points, and obstacles around the spacecraft to obtain corresponding 3D point cloud data. Then, the measurement station of the large-space 3D scanner is changed to ensure that the point cloud data covers all point cloud data of the area to be tested and the surrounding environment. By using the point cloud data and global control point information scanned from multiple stations, the point cloud data from all stations are stitched together to form complete point cloud data of the spacecraft structural surface and the surrounding environment in the same coordinate system.

[0096] After obtaining the point cloud data of the spacecraft structure surface and the surrounding environment, the complete point cloud data can be filtered, lightweighted and reverse-processed using point cloud 3D reverse engineering software to form a digital model file of the spacecraft structure surface and the surrounding environment structure, i.e., the spacecraft structure model file, thereby completing the on-site 3D model reconstruction of the spacecraft.

[0097] S103. Acquire images of the area to be inspected on the spacecraft, and establish the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system based on the calibration results.

[0098] It should be noted that the spacecraft to be inspected may include multiple regions, and the target relative pose relationship between the robot coordinate system and the spacecraft model coordinate system is used to characterize the mapping relationship between the robot and the spacecraft model.

[0099] After completing the test preparation phase, including system integration calibration and spacecraft on-site 3D model reconstruction, the mission implementation phase can begin. Please refer to [link to relevant documentation]. Figure 4 As shown, specifically, the transfer platform of the testing device can be adjusted to be near the area to be tested on the spacecraft and the robot's attitude can be adjusted. By adjusting the robot base to a suitable height and angle according to the distribution of the welds to be tested, the range of motion of the robot arm can cover as many welds as possible to be tested.

[0100] The inspection device utilizes visual sensors for image acquisition and processing. These sensors include a wide-field-of-view (HFOP) visual sensor and a local visual sensor. Once the robot approaches the working distance, the HFOP visual sensor at the robot's end effector acquires images of the spacecraft's inspection area. Understandably, to improve the weld inspection success rate, the HFOP visual sensor can capture multiple images of the spacecraft's inspection area from different angles during this stage, ensuring coverage of all welds within the inspection area.

[0101] After acquiring images of the spacecraft's inspection area, the robot's pose can be autonomously determined. Since the test station and its location are not fixed, the relative pose between the robot coordinate system and the spacecraft coordinate system is also random and unpredictable during each leak rate test. To plan the detection path and avoid obstacles based on the spacecraft structural model file reconstructed from the pre-test 3D scan, it is necessary to first determine the relative pose between the robot coordinate system and the spacecraft model coordinate system. In this application, a large field-of-view binocular vision sensor image can be used to reconstruct the 3D point cloud of the inspection area, obtaining global and local point cloud data. Then, a point cloud registration algorithm is used to register the local point cloud data with the spacecraft's global point cloud data, ultimately obtaining the relative pose between the robot coordinate system and the spacecraft coordinate system.

[0102] Please see Figure 5 As shown, Figure 5 The diagram shows the system calibration structure, where 1 is the robot coordinate system, 2 is the robot end effector flange coordinate system, 3 is the vision sensor coordinate system, 4 is the leak detection tool coordinate system, and 5 is the spacecraft model coordinate system. In determining the relative pose relationship between the robot coordinate system and the spacecraft coordinate system, based on the first relative pose relationship between the vision sensor coordinate system 3 and the robot coordinate system 1, and the second relative pose relationship between the leak detection tool coordinate system 4 and the robot coordinate system 1, the robot end effector flange coordinate system 2 can be considered as the robot coordinate system 1. A binocular stereo matching algorithm is used to determine the 3D point cloud data of the area to be detected in the robot coordinate system, and this 3D point cloud data is used as the data to be oriented. The point cloud data of the spacecraft structure surface and the surrounding environment are used as the target source data. Then, a 3D point cloud registration algorithm is used to register the data to be oriented and the target source data acquired by the vision sensor, thus determining the relative pose relationship between the robot coordinate system 1 and the spacecraft model coordinate system 5.

[0103] Specifically, a robot carrying a large field-of-view vision sensor can be controlled to move directly above the center of the pipeline area to be inspected on the spacecraft and acquire images of the area to be inspected, ensuring that the images cover all weld seams of the pipelines in the area to be inspected. Then, combined with the vision sensor calibration and hand-eye calibration data, i.e. based on the first relative pose relationship and the second relative pose relationship, a binocular stereo matching algorithm can be used to determine the three-dimensional point cloud data of the area to be inspected in the robot coordinate system. This three-dimensional point cloud data is used as the data to be oriented. Then, the point cloud data of the spacecraft structure surface and the surrounding environment are used as the target source data. The scanned point cloud data is used as the target source data. A three-dimensional point cloud registration algorithm is used to register the data to be oriented acquired by the vision sensor with the target source data, thereby determining the relative orientation relationship between the robot base coordinate system and the spacecraft model coordinate system.

[0104] S104. Based on the image of the area to be inspected on the spacecraft, determine the target location information and pipeline clamping attitude information of all welds to be inspected in the area to be inspected on the spacecraft.

[0105] The aforementioned spacecraft inspection area may include multiple weld seams to be inspected, each weld seam having a weld seam center. The target position information of the aforementioned weld seam to be inspected refers to the position information corresponding to the center point of the weld seam to be inspected.

[0106] Among them, the image of the spacecraft to be inspected can be obtained by the large field-of-view vision sensor in the vision sensor. After the image of the spacecraft to be inspected is obtained, the trained weld recognition model can be used to process the image of the spacecraft to be inspected, identify all the welds to be inspected in the image of the spacecraft to be inspected, and determine the target position information of the welds to be inspected.

[0107] Specifically, a large number of spacecraft pipeline sample images can be collected in advance to construct a training set, and the welds contained in the spacecraft pipeline sample images can be labeled to obtain the labeling results. Then, the training set can be trained based on a deep learning image recognition model to identify the features of the spacecraft pipeline welds and obtain the output results. Based on the output results and the labeling results, a loss function can be constructed. The deep learning image recognition model can be trained according to minimizing the loss function to obtain the weld recognition model.

[0108] After constructing the weld recognition model, the acquired images of the spacecraft's inspection area can be input into the weld recognition model for recognition processing. The coordinates of the center of the weld to be inspected in the image of the spacecraft's inspection area are determined. Based on the binocular vision epipolar matching algorithm, the corresponding weld images in the left and right camera images are matched. Then, combined with the binocular vision 3D reconstruction algorithm, the spatial 3D coordinates of the weld in the robot's base coordinate system can be determined, achieving coarse localization of all weld targets. Based on the coarse localization results, the robot can carry a vision sensor to reach directly above each weld to be inspected. Then, the local vision sensor in the vision sensor is used to acquire images of the weld to be inspected. The images are then recognized and processed by the weld recognition model to determine the center position information of the weld to be inspected and the pipe clamping attitude information, thereby achieving precise localization of the weld to be inspected.

[0109] In this embodiment, based on the image of the area to be inspected on the spacecraft, a weld seam recognition model can be constructed to accurately determine the target location information and pipeline clamping attitude information of all weld seams to be inspected.

[0110] S105. Based on the target position and attitude information, the spacecraft structural model file, and the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, the detection path is planned and the leak rate is tested for the weld to be inspected, and the leak rate test results of all welds to be inspected in the spacecraft to be inspected area are obtained.

[0111] In one embodiment, this application also provides a specific implementation method for performing leak rate testing on the welds to be inspected based on target location information, spacecraft structural model files, and target relative pose relationships, to obtain the leak rate test results for all welds to be inspected in the spacecraft's inspection area. Please refer to [link to implementation details]. Figure 6 As shown, the method includes:

[0112] S201. Based on the point cloud data of the spacecraft surface and the point cloud data of the surrounding environment, a planar feature algorithm is used to identify the planar point cloud data of the pipeline base plate. Based on the planar point cloud data of the pipeline base plate, a planar feature fitting algorithm is used to determine the planar normal vector information of the pipeline base plate.

[0113] S202. Based on the normal vector information of the pipeline base plate plane, adjust the leak rate detection tool to the initial attitude information; the initial attitude information is used to characterize that the leak rate detection tool is perpendicular to the pipeline base plate plane.

[0114] S203. Based on the spacecraft structural model file, the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, the target position information and attitude information of the weld to be inspected, plan the motion path for the inspection of the weld.

[0115] S204. Based on the motion path, a leak rate test is performed on the weld to be inspected to obtain the leak rate test results of all welds to be inspected in the spacecraft inspection area.

[0116] It should be noted that, due to the small diameter and dense distribution of the spacecraft's pipes, to avoid the risk of collision during inspection, the leak detection tool at the robot's end effector must clamp and hold the weld to be inspected in a perpendicular position to the base plate. Therefore, before planning the motion path, the attitude of the leak detection tool at the robot's end effector needs to be coarsely adjusted to provide initial attitude information for robot path planning. The initial attitude information is used to characterize that the leak detection tool is perpendicular to the plane of the pipe base plate.

[0117] To achieve precise clamping of pipeline welds, it is necessary to determine the attitude information of the end effector inspection tool. Specifically, this can be achieved by using images of the spacecraft's inspection area acquired by a large field-of-view vision sensor in the vision sensor, employing planar feature recognition algorithms to identify and extract the point cloud data of the pipeline base plate, and using planar feature fitting algorithms to determine the normal vector information of the pipeline base plate plane. Then, the robot's end effector leak detection tool axis is controlled to be perpendicular to the pipeline base plate plane, completing the coarse adjustment of the robot's end effector inspection tool attitude. Based on images acquired by a local vision sensor, the edges of the pipeline to be inspected are extracted to determine the pipeline's direction information in the image. Then, based on the robot's hand-eye calibration and the calibration results of the leak detection tool, the angle between the pipeline direction and the gripping direction of the end effector inspection tool's jaws can be determined. The end effector leak detection tool is then controlled to rotate around its tool axis, thereby achieving that the gripping direction of the jaws is parallel to the weld direction, completing the fine adjustment of the leak detection tool attitude.

[0118] Specifically, after determining the target position information of all welds to be inspected within the spacecraft's inspection area based on images of that area, a motion path for inspection can be planned based on the spacecraft structural model file, the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, and the target position and attitude information of the welds to be inspected. Then, based on the motion path, a leak rate test is performed on the welds to be inspected, yielding the leak rate test results for all welds to be inspected within the spacecraft's inspection area.

[0119] In one embodiment, this application also provides a specific implementation method for performing leak rate testing on the weld to be inspected based on the motion path, and obtaining the leak rate test results of all welds to be inspected in the spacecraft's inspection area. Please refer to [link to implementation details]. Figure 7 As shown, the method includes:

[0120] S301. Determine the weld to be inspected in ascending order of the weld inspection path. Repeat the specified operation until all welds to be inspected have been inspected.

[0121] The specified operations include:

[0122] S302. For the current weld to be inspected, based on the motion path, the leak rate detection tool is controlled by the robot to move to a position directly above the current weld to be inspected.

[0123] S303. Acquire an image of the weld to be inspected using a local vision sensor in the vision sensor.

[0124] S304. Based on the image of the weld to be inspected, determine the center position information and pipeline routing information of the weld to be inspected.

[0125] S305. Based on the center position information and pipeline routing information of the weld to be inspected, a leak rate test is performed on the weld to be inspected to obtain the leak rate test result corresponding to the weld to be inspected.

[0126] S306. Determine whether the current weld to be inspected is the last weld to be inspected among all welds to be inspected.

[0127] If it is not the last weld to be inspected, the control proceeds to the next specified operation; if it is the last weld to be inspected, the control does not proceed to the next specified operation.

[0128] S307, Output leak rate test results.

[0129] Specifically, after obtaining the motion path of each weld to be inspected, the current weld to be inspected can be determined according to the weld inspection order from shortest to longest motion path. Then, for the current weld to be inspected, based on the motion path, the robot controls the leak rate detection tool to move to a position directly above the current weld to be inspected, for example, to move it to a position 20 centimeters above. Then, the local vision sensor in the vision sensor collects the image of the current weld to be inspected, providing preparation information for subsequent precise positioning of the pipeline weld center and determination of the pipeline route.

[0130] After acquiring the image of the weld to be inspected, the image can be processed by a trained weld recognition model to determine the center position information of the weld and the pipeline direction information, thereby achieving accurate positioning of the weld. Specifically, the image of the weld to be inspected can be acquired by a local vision sensor, and the weld and pipeline direction can be accurately identified. Then, the center of the weld can be accurately located by combining binocular stereo matching and positioning algorithms, thus providing high-precision data information for the leak rate detection tool to accurately clamp the weld to be inspected.

[0131] After obtaining the center position information and pipeline routing information of the weld to be inspected, a leak rate test can be performed on the weld. Specifically, based on the center position information and pipeline routing information of the weld, the initial attitude information of the leak rate detection tool is adjusted to the target attitude information. The target attitude information is used to characterize the leak rate detection tool clamping the weld to be inspected, forming a sealed space by clamping and covering the weld. The concentration of the leak-indicating gas at the weld is detected by evacuation, and the leak rate test result corresponding to the weld is obtained. This leak rate test result is used to characterize whether there is a leak at the weld.

[0132] It should be noted that a local vision sensor can be used to precisely locate the weld seam to be inspected and finely adjust the attitude of the end tool. Then, the inspection tool is controlled to move along the tool axis to the target position of the weld seam to achieve precise clamping of the weld seam. During the clamping process, the six-degree-of-freedom force sensor at the end of the robot can detect the force on the end tool in real time. When the force value exceeds the set threshold, the robot will stop moving and issue an alarm indication. This alarm indication is used to indicate that the force is too large, so as to ensure that no damage is caused to the spacecraft pipeline during the inspection process.

[0133] Based on the center position information of the weld to be tested and the pipeline routing information, the robot's end effector leak detection tool's attitude is first fine-tuned so that it is perpendicular to the pipeline base plate plane and the gripper jaws are parallel to the weld routing. Then, the end effector's grippers are moved to the center of the weld, adjusting the initial attitude information of the leak detection tool to the target attitude information, ultimately achieving precise clamping of the weld. The detection tool's grippers then clamp and enclose the pipeline weld to form a sealed space. A helium mass spectrometer leak detector is used to detect the leakage gas concentration of the weld under test using a pumping method to obtain the leak rate value. This leak rate value is then compared with a preset threshold. If the leak rate value is greater than the preset threshold, a leak is determined to exist in the weld under test; if the leak rate value is not greater than the preset threshold, no leak is determined to exist. The preset threshold is a custom value set according to actual needs.

[0134] After completing the leak rate test on the current weld to be inspected, the next weld to be inspected can be determined according to the inspection sequence of the motion path. Then, the next weld to be inspected is tested in the same way as the previous weld to be inspected to obtain the leak rate test result of the next weld to be inspected. It is also determined whether the current weld to be inspected is the last weld to be inspected among all the welds to be inspected. If it is not the last weld to be inspected, the control enters the same way as the previous weld to be inspected to perform the test on the next weld to be inspected. If it is the last weld to be inspected, the process ends, thereby sequentially completing the clamping and leak rate test of all welds in the inspection area of ​​the spacecraft.

[0135] The spacecraft may include multiple areas to be tested. After all welds in the current area to be tested on the spacecraft have been tested, the next area to be tested can be determined. Then, in the same way as the current area to be tested, all welds in the next area to be tested are tested for leak rate until the leak rate test of all welds in the entire circumference of the spacecraft is completed.

[0136] In this embodiment, the posture information of the leak rate detection tool is precisely adjusted based on the image of each weld to be inspected, which facilitates the clamping and covering of the weld to be inspected, and enables accurate detection of the leaking gas concentration of the weld to be inspected, resulting in more accurate leak rate test results.

[0137] The testing method for spacecraft pipeline welds provided in this application involves calibrating the parameters of the vision sensor, robot, and leak rate detection tool in the testing device to obtain calibration results. Then, the acquired point cloud data of the spacecraft structure surface and the surrounding environment is processed to obtain a spacecraft structure model file. Next, an image of the area to be tested on the spacecraft is acquired, and the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system is established based on the calibration results. Based on the image of the area to be tested, the target position information and pipeline clamping attitude information of all welds to be tested in the area are determined. Finally, based on the target position information and attitude information, the spacecraft structure model file, and the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, a detection path is planned and a leak rate test is performed on the welds to be tested, yielding the leak rate test results for all welds to be tested in the area to be tested on the spacecraft. Compared with existing technologies, this technical solution does not rely on manual operation. By calibrating the parameters of the vision sensors, robots, and leak detection tools in the detection device, and by constructing a spacecraft structural model file, it provides data guidance for the subsequent detection device to accurately detect weld leak rates. Based on the image of the area to be inspected on the spacecraft, it can accurately determine the target location information and pipeline routing information of all welds to be inspected. This combines more comprehensive information to conduct leak rate testing on the welds to be inspected, realizing flexible, intelligent, and autonomous testing of welding leak rates in the pipeline system during the spacecraft assembly process. This further effectively improves the development efficiency and automation level of large spacecraft.

[0138] It should be noted that although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flowchart may be performed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0139] on the other hand, Figure 8 This is a schematic diagram of a testing device for spacecraft pipeline welds, provided as an embodiment of this application. This device can be a device located within a vehicle-mounted workstation, such as... Figure 8 As shown, the device 400 includes:

[0140] The calibration module 410 is used to perform parameter calibration processing on the vision sensor, robot and leak rate detection tool in the detection device to obtain calibration results;

[0141] The processing module 420 is used to process the acquired point cloud data of the spacecraft structure surface and the point cloud data of the surrounding environment to obtain the spacecraft structure model file.

[0142] The relationship establishment module 430 is used to acquire images of the area to be inspected on the spacecraft and establish the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system based on the calibration results.

[0143] The determination module 440 is used to determine the target position information and pipeline clamping attitude information of all welds to be inspected in the spacecraft's inspection area based on the image of the spacecraft's inspection area.

[0144] Test module 450 is used to perform detection path planning and leak rate testing on the weld to be inspected based on target position and attitude information, spacecraft structural model file and the relative pose relationship between robot coordinate system and spacecraft model coordinate system, and to obtain the leak rate test results of all welds to be inspected in the spacecraft inspection area.

[0145] In one embodiment, the test module 450 is specifically used for:

[0146] Based on point cloud data of spacecraft surface and surrounding environment, a planar feature algorithm is used to identify the planar point cloud data of pipeline base plate. Based on the planar point cloud data of pipeline base plate from a large field of view visual sensor, a planar feature fitting algorithm is used to determine the planar normal vector information of pipeline base plate.

[0147] Based on the normal vector information of the pipeline base plate plane, the leak rate detection tool is adjusted to the initial attitude information; the initial attitude information is used to characterize that the leak rate detection tool is perpendicular to the pipeline base plate plane;

[0148] Based on the spacecraft structural model file, the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, and the target position and attitude information of the weld to be inspected, a motion path for inspection is planned for the weld to be inspected.

[0149] Based on the motion path, a leak rate test is performed on the weld to be inspected, and the leak rate test results of all welds to be inspected in the spacecraft inspection area are obtained.

[0150] In one embodiment, the test module 450 is further configured to:

[0151] The current weld to be inspected is determined according to the weld inspection order from shortest to longest according to the motion path, and the specified operation is executed cyclically until all welds to be inspected have been inspected.

[0152] The specified operations include:

[0153] For the current weld to be inspected, based on the motion path, the leak rate detection tool is controlled by the robot to move to a position directly above the current weld to be inspected;

[0154] The image of the weld to be inspected is acquired by a local vision sensor in the vision sensor.

[0155] Based on the image of the weld to be inspected, determine the center position information of the weld to be inspected and the pipeline routing information;

[0156] Based on the center position information of the weld to be inspected and the pipeline routing information, a leak rate test is performed on the weld to be inspected to obtain the leak rate test result corresponding to the weld to be inspected.

[0157] Determine whether the current weld to be inspected is the last weld to be inspected among all welds to be inspected;

[0158] If it is not the last weld to be inspected, the control proceeds to the next specified operation; if it is the last weld to be inspected, the control does not proceed to the next specified operation.

[0159] In one embodiment, the test module 450 is further configured to:

[0160] Based on the center position information of the weld to be inspected and the pipeline routing information, the initial attitude information of the leak rate detection tool is adjusted to the target attitude information; the target attitude information is used to characterize the leak rate detection tool clamping the weld to be inspected.

[0161] The leak rate detection tool is used to clamp and cover the weld seam to be inspected to form a sealed space.

[0162] The concentration of leaking gas in the weld to be inspected is detected by evacuation, and the leak rate test result corresponding to the weld to be inspected is obtained.

[0163] In one embodiment, the determining module 440 is specifically used for:

[0164] Images of the spacecraft's target area are acquired using a large field-of-view vision sensor within the vision sensor suite.

[0165] The trained weld recognition model is used to process the image of the spacecraft's inspection area to identify all the welds to be detected in the image of the spacecraft's inspection area;

[0166] Determine the target location information of the weld to be inspected.

[0167] In one embodiment, the relationship establishment module 430 is specifically used for:

[0168] The parameters of the vision sensor, robot, and leak rate detection tool in the detection device were calibrated separately to obtain calibration results, including:

[0169] Select a vision calibration plate based on the field of view parameters of the vision sensor;

[0170] Determine the attribute parameters of the large field-of-view vision sensor and the local vision sensor in the vision sensor, and the first relative orientation relationship between the large field-of-view vision sensor and the local vision sensor;

[0171] Determine the second relative orientation relationship between the large field-of-view vision sensor coordinate system and the local vision sensor coordinate system;

[0172] Based on the first relative orientation relationship and the second relative orientation relationship, the large field of view visual sensor coordinate system is set as the visual sensor coordinate system;

[0173] Based on the vision calibration board, the first relative pose relationship between the vision sensor coordinate system and the robot coordinate system is determined, and the second relative pose relationship between the robot coordinate system and the leak rate detection tool coordinate system is determined.

[0174] In one embodiment, the relationship establishment module 430 is further configured to:

[0175] Based on the first relative pose relationship and the second relative pose relationship, a binocular stereo matching algorithm is used to determine the three-dimensional point cloud data of the area to be detected in the robot coordinate system, and the three-dimensional point cloud data is used as the data to be oriented.

[0176] Use point cloud data of the spacecraft's structural surface and point cloud data of the surrounding environment as target source data;

[0177] A 3D point cloud registration algorithm is used to register the data to be oriented and the target source data acquired by the vision sensor, thereby determining the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system.

[0178] The testing device for spacecraft pipeline welds provided in this application embodiment performs parameter calibration on the vision sensor, robot, and leak rate detection tool in the testing device to obtain calibration results. It then processes the acquired point cloud data of the spacecraft structure surface and the surrounding environment to obtain a spacecraft structure model file. Next, it acquires an image of the area to be tested on the spacecraft and establishes the target relative pose relationship between the robot coordinate system and the spacecraft model coordinate system based on the calibration results. Based on the image of the area to be tested on the spacecraft, it determines the target position information and pipeline clamping attitude information of all welds to be tested in the area. Finally, based on the target position and attitude information, the spacecraft structure model file, and the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, it performs detection path planning and leak rate testing on the welds to be tested, obtaining the leak rate test results for all welds to be tested in the area. Compared with existing technologies, this technical solution does not rely on manual operation. By calibrating the parameters of the vision sensors, robots, and leak detection tools in the detection device, and by constructing a spacecraft structural model file, it provides data guidance for the subsequent detection device to accurately detect weld leak rates. Based on the image of the area to be inspected on the spacecraft, it can accurately determine the target location information and pipeline routing information of all welds to be inspected. This combines more comprehensive information to conduct leak rate testing on the welds to be inspected, realizing flexible, intelligent, and autonomous testing of welding leak rates in the pipeline system during the spacecraft assembly process. This further effectively improves the development efficiency and automation level of large spacecraft.

[0179] On the other hand, the computer device provided in the embodiments of this application includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the testing method for spacecraft pipeline welds as described above.

[0180] The following is for reference. Figure 9 , Figure 9 This is a schematic diagram of the structure of the computer system of the ground station according to an embodiment of this application.

[0181] like Figure 9 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage portion 603 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the system 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0182] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0183] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a machine-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 603, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined above in the system of this application.

[0184] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0185] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0186] The units or modules described in the embodiments of this application can be implemented in software or hardware. The described units or modules can also be housed in a processor; for example, they can be described as: a processor including: a calibration module, a processing module, a relationship establishment module, and a determination module. The names of these units or modules do not necessarily limit the specific unit or module itself. For example, the calibration module can also be described as "used to perform parameter calibration processing on the visual sensor, robot, and leak rate detection tool in the detection device, respectively, to obtain calibration results."

[0187] In another aspect, this application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable storage medium stores one or more programs, which, when used by one or more processors, execute the testing method for spacecraft pipe welds described in this application:

[0188] The parameters of the vision sensor, robot, and leak rate detection tool in the detection device were calibrated to obtain the calibration results.

[0189] The acquired point cloud data of the spacecraft structure surface and the surrounding environment are processed to obtain the spacecraft structure model file;

[0190] Acquire images of the area to be inspected on the spacecraft, and establish the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system based on the calibration results;

[0191] Based on the image of the spacecraft's inspection area, determine the target location information and pipeline clamping attitude information of all welds to be inspected in the spacecraft's inspection area;

[0192] Based on the target position and attitude information, the spacecraft structural model file, and the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, the detection path is planned and the leak rate is tested for the weld to be inspected, and the leak rate test results of all welds to be inspected in the spacecraft inspection area are obtained.

[0193] In summary, the testing method, system, equipment, and storage medium for spacecraft pipeline welds provided in this application embodiment calibrates the parameters of the vision sensor, robot, and leak rate detection tool in the testing device to obtain calibration results. It then processes the acquired point cloud data of the spacecraft structure surface and the surrounding environment to obtain a spacecraft structure model file. Next, it acquires an image of the spacecraft's inspection area and establishes the target relative pose relationship between the robot coordinate system and the spacecraft model coordinate system based on the calibration results. Based on the image of the spacecraft's inspection area, it determines the target position information and pipeline clamping attitude information of all welds to be inspected in the inspection area. Finally, based on the target position and attitude information, the spacecraft structure model file, and the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, it performs inspection path planning and leak rate testing on the welds to be inspected, obtaining the leak rate test results for all welds to be inspected in the spacecraft's inspection area. Compared with existing technologies, this technical solution does not rely on manual operation. By calibrating the parameters of the vision sensors, robots, and leak detection tools in the detection device, and by constructing a spacecraft structural model file, it provides data guidance for the subsequent detection device to accurately detect weld leak rates. Based on the image of the area to be inspected on the spacecraft, it can accurately determine the target location information and pipeline routing information of all welds to be inspected. This combines more comprehensive information to conduct leak rate testing on the welds to be inspected, realizing flexible, intelligent, and autonomous testing of welding leak rates in the pipeline system during the spacecraft assembly process. This further effectively improves the development efficiency and automation level of large spacecraft.

[0194] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for testing a weld of a spacecraft pipe, the method comprising: The method includes: The parameters of the vision sensor, robot, and leak rate detection tool in the detection device were calibrated to obtain the calibration results. The acquired point cloud data of the spacecraft structure surface and the surrounding environment are processed to obtain the spacecraft structure model file; Acquire images of the area to be inspected on the spacecraft, and establish the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system based on the calibration results; Based on the image of the spacecraft's inspection area, determine the target location information and pipeline clamping attitude information of all welds to be inspected in the spacecraft's inspection area; Based on the target position information, the attitude information, the spacecraft structure model file, and the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, the detection path is planned and the leak rate is tested for the weld to be inspected, and the leak rate test results of all welds to be inspected in the spacecraft inspection area are obtained. Based on the center position information and pipeline routing information of the weld to be inspected, a leak rate test is performed on the weld to be inspected to obtain the leak rate test result corresponding to the weld to be inspected, including: Based on the center position information of the current weld to be inspected and the pipeline routing information, the initial posture information of the leak rate detection tool is adjusted to the target posture information; the target posture information is used to characterize the leak rate detection tool clamping the current weld to be inspected. The leak rate detection tool is used to clamp and cover the weld seam to be inspected to form a sealed space. The concentration of the leak-indicating gas in the current weld to be inspected is detected by evacuation, and the leak rate test result corresponding to the current weld to be inspected is obtained. The calibration results include a first relative pose relationship between the visual sensor coordinate system and the robot coordinate system, and a second relative pose relationship between the robot coordinate system and the leak rate detection tool coordinate system; The parameters of the vision sensor, robot, and leak rate detection tool in the detection device were calibrated separately to obtain calibration results, including: Select a visual calibration plate based on the field of view parameters of the visual sensor; Determine the attribute parameters of the large field-of-view visual sensor and the local visual sensor in the visual sensor, and the first relative orientation relationship between the large field-of-view visual sensor and the local visual sensor; Determine the second relative orientation relationship between the large field-of-view vision sensor coordinate system and the local vision sensor coordinate system; Based on the first relative orientation relationship and the second relative orientation relationship, the large field-of-view visual sensor coordinate system is set as the visual sensor coordinate system; Based on the vision calibration board, a first relative pose relationship between the vision sensor coordinate system and the robot coordinate system is determined, and a second relative pose relationship between the robot coordinate system and the leak rate detection tool coordinate system is determined. Establishing the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system includes: Based on the first relative pose relationship and the second relative pose relationship, a binocular stereo matching algorithm is used to determine the three-dimensional point cloud data of the area to be detected in the robot coordinate system, and the three-dimensional point cloud data is used as the orientation data; The point cloud data of the spacecraft's structural surface and the point cloud data of the surrounding environment are used as the target source data. A 3D point cloud registration algorithm is used to register the data to be oriented acquired by the vision sensor and the target source data to determine the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system.

2. The method of claim 1, wherein, Based on the target position information, the attitude information, the spacecraft structural model file, and the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, a detection path is planned and a leak rate test is performed on the weld to be inspected. The leak rate test results for all welds to be inspected in the spacecraft's inspection area are obtained, including: Based on the point cloud data of the spacecraft structure surface and the point cloud data of the surrounding environment, a planar feature algorithm is used to identify the planar point cloud data of the pipeline base plate. Based on the planar point cloud data of the pipeline base plate, a planar feature fitting algorithm is used to determine the planar normal vector information of the pipeline base plate. Based on the normal vector information of the pipeline base plate plane, the leak rate detection tool is adjusted to its initial attitude information; the initial attitude information is used to characterize that the leak rate detection tool is perpendicular to the pipeline base plate plane; Based on the spacecraft structural model file, the relative pose relationship between the robot coordinate system and the spacecraft model coordinate system, the target position information of the weld to be inspected, and the attitude information, a motion path for inspecting the weld to be inspected is planned. Based on the motion path, a leak rate test is performed on the weld to be tested, and the leak rate test results of all welds to be tested in the spacecraft's testing area are obtained.

3. The method according to claim 2, characterized in that, The visual sensor includes a local visual sensor and a large field-of-view visual sensor. Based on the motion path, a leak rate test is performed on the weld to be inspected to obtain the leak rate test results of all welds to be inspected in the spacecraft's inspection area, including: The current weld to be inspected is determined according to the weld inspection order from shortest to longest according to the motion path, and the specified operation is executed cyclically until all welds to be inspected have been inspected. The specified operation includes: For the current weld to be inspected, based on the motion path, the robot controls the leak rate detection tool to move to a position directly above the current weld to be inspected; The image of the weld seam to be inspected is acquired by a local vision sensor in the vision sensor. Based on the image of the weld to be inspected, determine the center position information and pipeline routing information of the weld to be inspected. Based on the center position information and pipeline routing information of the current weld to be inspected, a leak rate test is performed on the current weld to be inspected to obtain the leak rate test result corresponding to the current weld to be inspected. Determine whether the current weld to be inspected is the last weld to be inspected among all welds to be inspected; If the weld is not the last one to be inspected, the control proceeds to the next specified operation; if the weld is the last one to be inspected, the control does not proceed to the next specified operation.

4. The method according to claim 1, characterized in that, Based on the image of the area to be inspected on the spacecraft, the target location information of all welds to be inspected in the area to be inspected on the spacecraft is determined, including: The image of the spacecraft's target area is acquired by the large field-of-view vision sensor in the vision sensor; The trained weld recognition model is used to process the image of the spacecraft's inspection area to identify all the welds to be detected in the image of the spacecraft's inspection area. Determine the target location information of the weld to be inspected.

5. A testing system for welded seams in spacecraft piping, characterized in that, Based on the test method for spacecraft pipeline welds as described in any one of claims 1-4, the system includes: a spacecraft pipeline to be tested and a testing device, wherein the testing device includes a transfer platform, a robot, a vehicle-mounted workstation, a rotary lifting mechanism, a force sensor, a leak rate detection tool, and a vision sensor; The transfer platform is equipped with the vehicle-mounted workstation and the rotating lifting mechanism; the robot is connected to the rotating lifting mechanism, the force sensor, the leak detection tool, and the vision sensor respectively; the vehicle-mounted workstation is electrically connected to the transfer platform, the robot, the rotating lifting mechanism, the force sensor, the leak detection tool, and the vision sensor respectively.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the testing method for spacecraft pipeline welds as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, the computer program being used to implement the testing method for spacecraft piping welds as described in any one of claims 1-4.

Images