Satellite complex truss part assembly relationship guide mark automatic pasting system and method

Abstract

The application provides a satellite complex truss part assembly relationship guide mark automatic sticking system and method, which comprises a high-performance computer (101), a guide mark automatic sticking control system (102), a stereo camera module (103), a visual identification module (104), a part grabbing module (105), a mark sticking module (106), a workbench (107), a guide mark printer (108) and a guide mark (109). The application can automatically analyze the complex truss assembly relationship and generate a guide mark information database, automatically grab the truss parts to adjust the pose and identify, automatically print the assembly relationship guide mark and stick it at the specified position of the part, realize the automation operation of the guide mark sticking process, improve the satellite truss development efficiency and the digital level, and provide support for ensuring the one-time assembly success of the satellite complex truss.

Description

Technical Field

[0001] This invention belongs to the field of satellite truss assembly technology, specifically, it relates to an automatic pasting system and method for guiding the assembly relationship of complex satellite truss parts. Background Technology

[0002] Truss structures are a common structural form in satellites, mainly assembled from carbon fiber rods and multi-joints, and have advantages such as lightweight, high rigidity, diverse forms, and flexible design. With the continuous development of payloads such as high-resolution, high-sensitivity space cameras and satellite antennas, satellite truss structures are showing a trend towards larger and more complex sizes, with envelope dimensions exceeding 3000 mm, topological configurations exhibiting spatial asymmetry, fully closed rod systems, and hundreds of parts such as rods and joints, making it increasingly difficult to ensure successful assembly on the first attempt.

[0003] Currently, the main method for identifying truss components is through manual comparison of 3D models, followed by the application of assembly relationship guidance markers. Due to the large number of truss components and the high degree of similarity among some parts, the application of guidance markers is labor-intensive and carries the risk of misjudgment, potentially leading to assembly errors in complex truss structures. Patent document "An Assembly Guidance Method, System and Application Based on Augmented Reality" (CN112734945A) discloses a method and system for assembly guidance based on the 3D edge contour feature information of components; however, it directly uses contour information as guidance information through camera recognition without improving the marking method for guidance information.

[0004] Therefore, a method is needed to automatically attach guidance marks for the assembly relationship of complex satellite truss parts, thereby automating the process of attaching guidance marks, improving the efficiency and digitalization level of satellite truss development, and providing support for ensuring the successful one-time assembly of complex satellite trusses. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the purpose of this invention is to provide an automatic pasting system and method for guiding the assembly relationships of complex satellite truss components.

[0006] The automatic labeling system for guiding the assembly relationship of complex satellite truss parts provided by the present invention includes: a high-performance computer 101, an automatic labeling control system 102, a stereo camera module 103, a vision recognition module 104, a parts gripping module 105, a labeling module 106, a workbench 107, a label printer 108, and a label 109.

[0007] A high-performance computer analyzes the assembly relationships based on the three-dimensional model information of the satellite's complex truss and the assembly process information, generates assembly relationship guidance mark information for all m parts, and establishes a database of part assembly relationship guidance marks. Traverse all m parts, the stereo camera module takes pictures of part i (i=1, 2, ..., m) to obtain point cloud data, and the high-performance computer analyzes and calculates the point cloud data to locate part i and obtain positioning information; The parts grasping module grasps part i into the field of view of the vision recognition module based on the positioning information; The visual recognition module performs multi-view imaging on part i to obtain multiple images of part i; High-performance computers detect part labels from multiple images, calculate label pose, and determine occlusion. The part grasping module adjusts the position of part i to the correct position based on the label pose; The visual recognition module images the label on part i to obtain the label image; A high-performance computer processes the label images, identifies the content of the label images, and retrieves the corresponding assembly relationship guidance mark information from the parts assembly relationship guidance mark database; Iterate through all guide marks of part i, and print guide mark j using the guide mark printer based on the assembly relationship guide mark information; Where j = 1, 2, ..., n, n represents the number of guide marks for part i; The marker pasting module picks up the guide marker j; A high-performance computer plans the pasting path and determines the path solution based on the pose of part i and guide marker j; The marker pasting module pastes guide marker j at the specified position of part i, checks the task progress, and ends the pasting process.

[0008] Preferably, the high-performance computer analyzes and calculates point cloud data and label pose using the SGBM stereo matching algorithm, detects part labels using the YOLO target detection algorithm, identifies label image content using the optical character recognition algorithm, and plans the pasting path using the fast exploration random tree algorithm.

[0009] The multi-view imaging has no fewer than four viewpoints, and the obtained multiple images of part i are no fewer than four.

[0010] The occlusion determination is to determine whether the label of part i is occluded. If so, the part grasping module puts down part i and repositions part i to change the grasping position. If not, the part grasping module adjusts the pose of part i to the correct position.

[0011] The adjustment of part i's pose is to ensure that the normal vector at the center of the part label coincides with the optical axis of the camera lens of the visual recognition module, and is within the depth of field of the visual recognition module.

[0012] The marker pasting module picks up the guide markers through vacuum adsorption and pastes them using a flexible pressure method.

[0013] The determination of the path solution is to determine whether there is a solution for the pasting path. If there is, the marker pasting module adjusts the pose of the guide marker j; if not, the part grabbing module adjusts the pose of part i and replans the pasting path.

[0014] The judgment task process is to determine whether all guide marks of part i have been traversed. If not, let a=j, j=a+1, and the guide mark printer continues to print the next guide mark j. If yes, then determine whether all parts of the truss have been traversed. If yes, then end the pasting. If not, let a=i, i=a+1, and the high-performance computer continues to locate the next part i.

[0015] Preferably, the high-performance computer includes a host, a monitor, a keyboard, and a mouse, with the host electrically connected to the monitor, keyboard, and mouse respectively.

[0016] The automatic label pasting control system is electrically connected to a high-performance computer and includes a stereo camera module control circuit, a vision recognition module control circuit, a parts gripping module control circuit, and a label pasting module control circuit, which are electrically connected to the stereo camera module, the vision recognition module, the parts gripping module, and the label pasting module, respectively.

[0017] The stereo camera module includes an image sensor, a lens, a laser, and a laser galvanometer.

[0018] The visual recognition module includes an industrial camera, a camera lens, a lighting source, and a mounting bracket.

[0019] The parts gripping module includes a gripping industrial robotic arm and a gripping end effector.

[0020] The marking and pasting module includes marking industrial robotic arms and marking end effectors.

[0021] The workbench provides operating space for the parts gripping module and the marking and pasting module.

[0022] Preferably, the host has a processor with a clock speed of not less than 3.0 GHz, memory of not less than 32 GB, dedicated graphics card memory of not less than 16 GB, and hard disk of not less than 1 TB.

[0023] The display size is not less than 27 inches.

[0024] The image sensors are used to generate digital images with a resolution of not less than 10 million pixels, and there are no fewer than two of them.

[0025] The lenses are used to change light, with a field of view of not less than 50°, and their number is consistent with the number of image sensors.

[0026] The laser is used to generate line lasers, and the number of line lasers is no less than 7.

[0027] The laser galvanometer is used to scan the surface of the object being measured with a line laser at a frequency of not less than 1 Hz.

[0028] The industrial cameras are used to generate digital images with a resolution of no less than 10 million pixels, and the number of cameras is no less than four.

[0029] The camera lens is used to change the light, with a field of view of not less than 40°, and the number is consistent with the number of industrial cameras.

[0030] The lighting source is a white LED light source used to illuminate the target.

[0031] The mounting bracket is used to secure an industrial camera.

[0032] The gripping industrial robotic arm is a six-degree-of-freedom serial industrial robotic arm with a load capacity of not less than 10 kg, used to adjust the position and posture of the gripped part.

[0033] The gripping end effector has a maximum gripping diameter of not less than Φ100mm and a maximum gripping mass of not less than 6kg, and is used to grip truss parts.

[0034] The adhesive bonding industrial robotic arm is a six-degree-of-freedom serial industrial robotic arm with a load capacity of not less than 5 kg, used to adjust the position and posture of the guide markers.

[0035] The pasting end effector is used to pick up and paste the guide marker.

[0036] Preferably, the high-performance computer is used to set up, manage, and analyze the automatic pasting process of guidance marks for the assembly relationship of complex satellite truss parts.

[0037] The automatic label pasting control system is used to control the stereo camera module, vision recognition module, parts gripping module, and label pasting module to achieve imaging control, gripping control, and pasting control.

[0038] The stereo camera module is used for laser scanning and multi-view imaging of the parts.

[0039] The visual recognition module is used to image the parts and their labels.

[0040] The part gripping module is used to grip and adjust the position of parts.

[0041] The marker pasting module is used to pick up, adjust the pose of, and paste guide markers.

[0042] The workbench is used to place truss parts, a high-performance computer, and a guide marking printer, and is equipped with a stereo camera module, a vision recognition module, a parts gripping module, and a marking pasting module.

[0043] The guide mark printer is used to print assembly relationship guide marks that can be pasted.

[0044] The guide markers are used to display assembly relationship guidance information.

[0045] An automatic pasting method for guiding the assembly relationship of complex satellite truss parts according to the present invention includes: Step S1: Analyze the assembly relationships in a high-performance computer based on the 3D model information of the complex satellite truss and the assembly process information; Step S2: Have a high-performance computer generate assembly relationship guidance mark information for all m parts, establish a part assembly relationship guidance mark database, and traverse all m parts; Step S3: The stereo camera module captures point cloud data of part i (i=1, 2, ..., m), and the high-performance computer analyzes and calculates the point cloud data to locate part i and obtain positioning information; Step S4: Instruct the part grasping module to grasp part i into the field of view of the vision recognition module based on the positioning information; Step S5: Instruct the visual recognition module to perform multi-view imaging of part i to obtain multiple images of part i; Step S6: Instruct a high-performance computer to detect part labels based on multiple images and calculate the label pose; Step S7: Have the high-performance computer determine the occlusion; Step S8: Instruct the part grasping module to adjust the position of part i to the correct position according to the label pose; Step S9: Instruct the vision recognition module to image the label on part i to obtain the label image; Step S10: Process the label images in a high-performance computer to identify the label image content; Step S11: Instruct the high-performance computer to retrieve the corresponding assembly relationship guidance mark information from the part assembly relationship guidance mark database; Step S12: Let all guide marks of part i be traversed, and the guide mark printer prints guide mark j according to the assembly relationship guide mark information; Where j = 1, 2, ..., n, n represents the number of guide marks for part i; Step S13: Instruct the marker pasting module to pick up the guide marker j; Step S14: Instruct the high-performance computer to plan the pasting path and determine the path solution based on the pose of part i and guide marker j; Step S15: Instruct the marker pasting module to paste the guide marker j at the specified position of part i; Step S16: Check the task progress and end the pasting process.

[0046] Preferably, the high-performance computer analyzes and calculates point cloud data and label pose using the SGBM stereo matching algorithm, detects part labels using the YOLO target detection algorithm, identifies label image content using the optical character recognition algorithm, and plans the pasting path using the fast exploration random tree algorithm.

[0047] The marker pasting module picks up the guide markers through vacuum adsorption and pastes them using a flexible pressure method.

[0048] In step S5, the multi-view imaging has no fewer than four viewpoints, and the obtained multiple images of part i are no fewer than four.

[0049] In step S7, it is determined whether the label of part i is obscured. If so, the part grasping module puts down part i and executes step S3. If not, step S8 is executed.

[0050] In step S8, the part grasping module makes the normal vector at the center of the part label coincide with the optical axis of the camera lens of the visual recognition module, and within the depth of field range of the visual recognition module.

[0051] In step S14, it is determined whether there is a solution for the pasting path. If yes, step S15 is executed. If no, the part grabbing module adjusts the pose of part i and executes step S14 to replan the pasting path.

[0052] In step S16, it is determined whether all guide marks of part i have been traversed. If not, let a=j, j=a+1, and execute step S12. If yes, it is determined whether all parts of the truss have been traversed. Determine if all parts of the truss have been traversed. If yes, end the pasting process. If not, set a=i, i=a+1, and execute step S3.

[0053] Preferably, the high-performance computer includes a host, a monitor, a keyboard, and a mouse, with the host electrically connected to the monitor, keyboard, and mouse respectively.

[0054] The automatic label pasting control system is electrically connected to a high-performance computer and includes a stereo camera module control circuit, a vision recognition module control circuit, a parts gripping module control circuit, and a label pasting module control circuit, which are electrically connected to the stereo camera module, the vision recognition module, the parts gripping module, and the label pasting module, respectively.

[0055] The stereo camera module includes an image sensor, a lens, a laser, and a laser galvanometer.

[0056] The visual recognition module includes an industrial camera, a camera lens, a lighting source, and a mounting bracket.

[0057] The parts gripping module includes a gripping industrial robotic arm and a gripping end effector.

[0058] The marking and pasting module includes marking industrial robotic arms and marking end effectors.

[0059] The workbench provides operating space for the parts gripping module and the marking and pasting module.

[0060] Preferably, the host has a processor with a clock speed of not less than 3.0 GHz, memory of not less than 32 GB, dedicated graphics card memory of not less than 16 GB, and hard disk of not less than 1 TB.

[0061] The display size is not less than 27 inches.

[0062] The image sensors are used to generate digital images with a resolution of not less than 10 million pixels, and there are no fewer than two of them.

[0063] The lenses are used to change light, with a field of view of not less than 50°, and their number is consistent with the number of image sensors.

[0064] The laser is used to generate line lasers, and the number of line lasers is no less than 7.

[0065] The laser galvanometer is used to scan the surface of the object being measured with a line laser at a frequency of not less than 1 Hz.

[0066] The industrial cameras are used to generate digital images with a resolution of no less than 10 million pixels, and the number of cameras is no less than four.

[0067] The camera lens is used to change the light, with a field of view of not less than 40°, and the number is consistent with the number of industrial cameras.

[0068] The lighting source is a white LED light source used to illuminate the target.

[0069] The mounting bracket is used to secure an industrial camera.

[0070] The gripping industrial robotic arm is a six-degree-of-freedom serial industrial robotic arm with a load capacity of not less than 10 kg, used to adjust the position and posture of the gripped part.

[0071] The gripping end effector has a maximum gripping diameter of not less than Φ100mm and a maximum gripping mass of not less than 6kg, and is used to grip truss parts.

[0072] The adhesive bonding industrial robotic arm is a six-degree-of-freedom serial industrial robotic arm with a load capacity of not less than 5 kg, used to adjust the position and posture of the guide markers.

[0073] The pasting end effector is used to pick up and paste the guide marker.

[0074] Preferably, the high-performance computer is used to set up, manage, and analyze the automatic pasting process of guidance marks for the assembly relationship of complex satellite truss parts.

[0075] The automatic label pasting control system is used to control the stereo camera module, vision recognition module, parts gripping module, and label pasting module to achieve imaging control, gripping control, and pasting control.

[0076] The stereo camera module is used for laser scanning and multi-view imaging of the parts.

[0077] The visual recognition module is used to image the parts and their labels.

[0078] The part gripping module is used to grip and adjust the position of parts.

[0079] The marker pasting module is used to pick up, adjust the pose of, and paste guide markers.

[0080] The workbench is used to place truss parts, a high-performance computer, and a guide marking printer, and is equipped with a stereo camera module, a vision recognition module, a parts gripping module, and a marking pasting module.

[0081] The guide mark printer is used to print assembly relationship guide marks that can be pasted.

[0082] The guide markers are used to display assembly relationship guidance information.

[0083] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention can automatically analyze complex truss assembly relationships and generate a database of guiding mark information, thereby improving the efficiency and digitalization level of satellite truss development.

[0084] 2. This invention can automatically grasp truss parts, adjust their position and identify them, automatically print assembly relationship guidance marks and paste them at designated positions on the parts, thus automating the process of pasting the guidance marks.

[0085] 3. Compared with traditional methods, the present invention simplifies the workload and reduces the risk of misjudgment in the pasting of guide marks, thus providing support for ensuring the successful one-time assembly of complex satellite trusses. Attached Figure Description

[0086] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 A schematic diagram of an automatic pasting system for guiding the assembly relationships of complex truss components in satellites.

[0087] Figure 2A schematic diagram of a method for automatically pasting guide marks for the assembly relationships of complex truss components in satellites. Detailed Implementation

[0088] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0089] This invention can automatically analyze complex truss assembly relationships and generate a guide mark information database, automatically grasp truss parts, adjust their positions and identify them, automatically print assembly relationship guide marks and paste them at designated locations on the parts, thus automating the guide mark pasting process and improving the efficiency and digitalization level of satellite truss development. This invention provides an automatic pasting system for guide marks on complex satellite truss parts assembly relationships. Figure 1 For example, it specifically includes: a high-performance computer 101, an automatic guide mark pasting control system 102, a stereo camera module 103, a vision recognition module 104, a parts gripping module 105, a mark pasting module 106, a workbench 107, a guide mark printer 108, and a guide mark 109.

[0090] The high-performance computer is used to set up, manage, and analyze the automatic pasting process of guide markers for the assembly relationships of complex satellite truss parts. Through the high-performance computer and the automatic guide marker pasting control system, parameter setting, process management, data analysis, and motion control are achieved, enabling human-computer interaction, model analysis, label detection, pose estimation, part recognition, grasping analysis, pasting analysis, and data management.

[0091] In more preferred embodiments, the high-performance computer includes: a host computer, a monitor, a keyboard, and a mouse. The host computer is electrically connected to the monitor, keyboard, and mouse. The host computer has a processor with a clock speed of not less than 3.0 GHz, memory of not less than 32 GB, a dedicated graphics card with a video memory of not less than 16 GB, a hard disk of not less than 1 TB, and a monitor size of not less than 27 inches.

[0092] The automatic label pasting control system is used to control the stereo camera module, vision recognition module, parts grasping module, and label pasting module to achieve imaging control, grasping control, and pasting control.

[0093] The automatic guide marker pasting control system includes a stereo camera module control loop, a vision recognition module control loop, a parts gripping module control loop, and a marker pasting module control loop, which are electrically connected to the stereo camera module, vision recognition module, parts gripping module, and marker pasting module, respectively. The automatic guide marker pasting control system is also electrically connected to a high-performance computer.

[0094] The stereo camera module is used to perform laser scanning and multi-view imaging of truss parts, and to locate the truss parts by acquiring point cloud data of the parts and positioning the parts.

[0095] The stereo camera module includes: an image sensor, a lens, a laser, and a laser galvanometer. The image sensor is used to generate digital images, with a resolution of no less than 10 megapixels, and there are at least two of them. The lens is used to change the light, with a field of view of no less than 50°, and the number is the same as that of the image sensor. The laser is used to generate line lasers, and the number of line lasers is no less than seven. The laser galvanometer is used to scan the surface of the object being measured with the line lasers, and the scanning frequency is no less than 1Hz.

[0096] The visual recognition module is used to image truss parts and their labels, and to recognize truss parts, acquire part images and label images, and recognize label content.

[0097] The visual recognition module includes: an industrial camera, camera lenses, an illumination source, and a mounting bracket. The industrial camera is used to generate digital images, with a resolution of no less than 10 megapixels, and a quantity of no fewer than four. The camera lenses are used to modify the light, with a field of view of no less than 40°, and the number is consistent with that of the industrial camera. The illumination source is a white LED light source used to illuminate the target. The mounting bracket is used to fix the industrial camera.

[0098] The part gripping module is used to grip and adjust the pose of truss parts. The part gripping module is used to adjust the pose of truss parts, realize pose adjustment in the part recognition process, realize pose adjustment and part fixation in the guide mark pasting process.

[0099] The parts gripping module includes a gripping industrial robotic arm and a gripping end effector. The gripping industrial robotic arm is used to adjust the position and orientation of the gripped truss parts. It is a six-degree-of-freedom serial industrial robotic arm with a load capacity of not less than 10 kg. The gripping end effector is used to grip the truss parts, with a maximum gripping diameter of not less than Φ100 mm and a maximum gripping mass of not less than 6 kg.

[0100] The marker pasting module is used to pick up, adjust the position and paste the guide markers. The marker pasting module is used to paste the guide markers and realize the pasting of the assembly relationship guide markers at the specified positions of the truss parts.

[0101] The marking and pasting module includes: a pasting industrial robotic arm and a pasting end effector. The pasting industrial robotic arm is used to adjust the position and posture of the guide mark. It is a six-degree-of-freedom serial industrial robotic arm with a load capacity of not less than 5 kg. The pasting end effector is used to pick up and paste the guide mark. It picks up the guide mark by vacuum adsorption and pastes the guide mark by flexible pressure.

[0102] The workbench is used to place truss parts, high-performance computers, and guide marking printers, and to install stereo camera modules, vision recognition modules, parts gripping modules, and marking and pasting modules, and to provide operating space for the parts gripping modules and marking and pasting modules; The guide mark printer is used to print assembly relationship guide marks that can be pasted. The guide markers are used to display assembly relationship guidance information, which facilitates operators in assembling complex trusses.

[0103] In more preferred examples, a high-performance computer analyzes the assembly relationships based on the three-dimensional model information of the satellite complex truss and the assembly process information, generates assembly relationship guidance mark information for all m parts, and establishes a part assembly relationship guidance mark database. Iterate through all m parts, the stereo camera module takes pictures of part i (i=1, 2, ..., m) to obtain point cloud data, and the high-performance computer analyzes and calculates the point cloud data to locate part i and obtain positioning information.

[0104] The part grasping module grasps part i into the field of view of the vision recognition module based on the positioning information.

[0105] The visual recognition module performs multi-view imaging on part i to obtain multiple images of part i.

[0106] High-performance computers detect part labels based on multiple images, calculate label pose, and determine occlusion.

[0107] The part grasping module adjusts the position of part i to the correct position based on the label pose.

[0108] The visual recognition module images the label on part i to obtain the label image.

[0109] A high-performance computer processes the label images, identifies the content of the label images, and retrieves the corresponding assembly relationship guidance mark information from the parts assembly relationship guidance mark database; Iterate through all guide marks of part i, and print guide mark j using the guide mark printer based on the assembly relationship guide mark information; Where j = 1, 2, ..., n, and n represents the number of guide marks for part i.

[0110] The marker pasting module picks up the guide marker j.

[0111] A high-performance computer plans the pasting path and determines the path solution based on the pose of part i and guide marker j; The marker pasting module pastes guide marker j at the specified position of part i, checks the task progress, and ends the pasting process.

[0112] Specifically, the high-performance computer analyzes and calculates point cloud data and label pose using the SGBM stereo matching algorithm, detects part labels using the YOLO target detection algorithm, identifies label image content using the optical character recognition algorithm, and plans the pasting path using the fast exploration random tree algorithm.

[0113] The multi-view imaging has no fewer than four viewpoints, and the obtained multiple images of part i are no fewer than four.

[0114] The occlusion determination is to determine whether the label of part i is occluded. If so, the part grasping module puts down part i and repositions part i to change the grasping position. If not, the part grasping module adjusts the pose of part i to the correct position.

[0115] The adjustment of part i's pose is to ensure that the normal vector at the center of the part label coincides with the optical axis of the camera lens of the visual recognition module, and is within the depth of field of the visual recognition module.

[0116] The marker pasting module picks up the guide markers through vacuum adsorption and pastes them using a flexible pressure method.

[0117] The determination of the path solution is to determine whether there is a solution for the pasting path. If there is, the marker pasting module adjusts the pose of the guide marker j; if not, the part grabbing module adjusts the pose of part i and replans the pasting path.

[0118] The judgment task process is to determine whether all guide marks of part i have been traversed. If not, let a=j, j=a+1, and the guide mark printer continues to print the next guide mark j. If yes, then determine whether all parts of the truss have been traversed. If yes, then end the pasting. If not, let a=i, i=a+1, and the high-performance computer continues to locate the next part i.

[0119] The present invention provides an automatic pasting method for guiding the assembly relationship of complex satellite truss parts, so as to... Figure 2 For example, the steps include the following: Step S1: Open the 3D model of the complex truss of the satellite in a high-performance computer, and analyze the assembly relationship using a secondary development plugin based on the model's own information and assembly process information. Step S2: Automatically generate assembly relationship guidance mark information for all m truss parts, establish a truss part assembly relationship guidance mark database, and traverse all m parts of the satellite complex truss; Step S3: The stereo camera module captures point cloud data of truss part i (i=1, 2, ..., m, where m is the number of parts). The point cloud data is then analyzed and calculated using the SGBM (Semi-Global Block Matching) stereo matching algorithm in a high-performance computer to locate truss part i. Step S4: Based on the positioning information of truss part i, the part grasping module automatically grasps truss part i into the field of view of the vision recognition module; Step S5: Since it is necessary to identify the content of the part label to retrieve the corresponding assembly relationship, and the part label may be pasted on any surface of the part, the vision recognition module needs to perform multi-view imaging on the truss part i, with no less than 4 viewpoints, to obtain multiple images of the truss part i, with no less than 4 images, so that the imaging range can cover any surface of the part and ensure that the part label image is obtained. Step S6: Based on multiple images of truss part i, use the YOLO (You Only LookOnce) target detection algorithm in a high-performance computer to automatically detect part labels in the images, and use the SGBM stereo matching algorithm to calculate the label pose; Step S7: Determine whether the label of truss part i is obscured. If yes, the part gripping module puts down truss part i and executes step S3 to change the gripping position. If no, execute step S8. Step S8: Since the optimal imaging range of the visual recognition module is limited, it is necessary to adjust the part pose according to the part label pose in order to better image the part label. Specifically, the part grasping module adjusts the pose of the truss part i to the correct position so that the normal vector at the center of the part label coincides with the optical axis of the camera lens of the visual recognition module. At the same time, the part label is within the depth of field of the visual recognition module to ensure that the visual recognition module can perform vertical and clear imaging of the part label area. Step S9: The visual recognition module images the label on truss part i to obtain the label image; Step S10: Process the label image of truss part i in a high-performance computer and use the Optical Character Recognition (OCR) algorithm to automatically recognize the label content; Step S11: Based on the recognition results of the truss part i tag content, retrieve the corresponding assembly relationship guidance tag information in the truss part assembly relationship guidance tag database; Step S12: Traverse all guide marks of truss part i. Based on the assembly relationship guide mark information, the guide mark printer prints guide mark j (j=1, 2, ..., n, where n is the number of guide marks of truss part i). Step S13: The marker pasting module automatically picks up the guide marker j through vacuum adsorption; Step S14: Based on the pose of truss part i and the pose of guide marker j, the Rapidly-exploring Random Tree (RRT) algorithm is used in a high-performance computer to plan the pasting path and determine whether there is a solution for the pasting path. If yes, then proceed to step S15. If no, then the part grabbing module adjusts the pose of truss part i and proceeds to step S14 to replan the pasting path. Step S15: The marker pasting module adjusts the pose of the guide marker j and automatically pastes the guide marker j at the specified position of the truss part i by means of flexible pressure. Step S16: Determine whether all guide markers of truss part i have been traversed. If yes, determine whether all parts of the truss have been traversed. If no, continue to the next guide marker and execute step S12. If all parts of the truss have been traversed, the process ends; otherwise, it continues to the next part and executes step S3.

[0120] In more preferred embodiments, the high-performance computer includes a host, a monitor, a keyboard, and a mouse, with the host electrically connected to the monitor, keyboard, and mouse respectively.

[0121] The automatic label pasting control system is electrically connected to a high-performance computer and includes a stereo camera module control circuit, a vision recognition module control circuit, a parts gripping module control circuit, and a label pasting module control circuit, which are electrically connected to the stereo camera module, the vision recognition module, the parts gripping module, and the label pasting module, respectively.

[0122] The stereo camera module includes an image sensor, a lens, a laser, and a laser galvanometer.

[0123] The visual recognition module includes an industrial camera, a camera lens, a lighting source, and a mounting bracket.

[0124] The parts gripping module includes a gripping industrial robotic arm and a gripping end effector.

[0125] The marking and pasting module includes marking industrial robotic arms and marking end effectors.

[0126] The workbench provides operating space for the parts gripping module and the marking and pasting module.

[0127] Specifically, the high-performance computer is used to set up, manage, and analyze the automatic pasting process of guidance marks for the assembly relationship of complex satellite truss parts.

[0128] The automatic label pasting control system is used to control the stereo camera module, vision recognition module, parts gripping module, and label pasting module to achieve imaging control, gripping control, and pasting control.

[0129] The stereo camera module is used for laser scanning and multi-view imaging of the parts.

[0130] The visual recognition module is used to image the parts and their labels.

[0131] The part gripping module is used to grip and adjust the position of parts.

[0132] The marker pasting module is used to pick up, adjust the pose of, and paste guide markers.

[0133] The workbench is used to place truss parts, a high-performance computer, and a guide marking printer, and is equipped with a stereo camera module, a vision recognition module, a parts gripping module, and a marking pasting module.

[0134] The guide mark printer is used to print assembly relationship guide marks that can be pasted.

[0135] The guide markers are used to display assembly relationship guidance information.

[0136] In more preferred embodiments, the host's processor has a clock speed of not less than 3.0 GHz, memory of not less than 32 GB, dedicated graphics card memory of not less than 16 GB, and hard drive memory of not less than 1 TB.

[0137] The display size is not less than 27 inches.

[0138] The image sensors are used to generate digital images with a resolution of not less than 10 million pixels, and there are no fewer than two of them.

[0139] The lenses are used to change light, with a field of view of not less than 50°, and their number is consistent with the number of image sensors.

[0140] The laser is used to generate line lasers, and the number of line lasers is no less than 7.

[0141] The laser galvanometer is used to scan the surface of the object being measured with a line laser at a frequency of not less than 1 Hz.

[0142] The industrial cameras are used to generate digital images with a resolution of no less than 10 million pixels, and the number of cameras is no less than four.

[0143] The camera lens is used to change the light, with a field of view of not less than 40°, and the number is consistent with the number of industrial cameras.

[0144] The lighting source is a white LED light source used to illuminate the target.

[0145] The mounting bracket is used to secure an industrial camera.

[0146] The gripping industrial robotic arm is a six-degree-of-freedom serial industrial robotic arm with a load capacity of not less than 10 kg, used to adjust the position and posture of the gripped part.

[0147] The gripping end effector has a maximum gripping diameter of not less than Φ100mm and a maximum gripping mass of not less than 6kg, and is used to grip truss parts.

[0148] The adhesive bonding industrial robotic arm is a six-degree-of-freedom serial industrial robotic arm with a load capacity of not less than 5 kg, used to adjust the position and posture of the guide markers.

[0149] The pasting end effector is used to pick up and paste the guide marker.

[0150] This invention automates the process of attaching guide marks during the assembly of complex satellite truss components. It utilizes a high-performance computer and an automatic guide mark attachment control system to achieve parameter setting, process management, data analysis, and motion control. A stereo camera module is used to locate the truss components, a vision recognition module is used to identify the truss components, a component gripping module is used to adjust the pose of the truss components, and a mark attachment module is used to attach the guide marks. Ultimately, this automates the guide mark attachment process, improving the efficiency and digitalization level of satellite truss development.

[0151] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. An automatic pasting system for guiding the assembly relationship of complex satellite truss parts, characterized in that, include: High-performance computer 101, automatic guide mark pasting control system (102), stereo camera module (103), vision recognition module (104), part gripping module (105), mark pasting module (106), workbench (107), guide mark printer (108) and guide mark (109); A high-performance computer analyzes the assembly relationships based on the three-dimensional model information of the satellite's complex truss and the assembly process information, generates assembly relationship guidance mark information for all m parts, and establishes a database of part assembly relationship guidance marks. Traverse all m parts, the stereo camera module takes pictures of part i to obtain point cloud data, i=1,2,...,m, and the high-performance computer analyzes and calculates the point cloud data to locate part i and obtain positioning information; The parts grasping module grasps part i into the field of view of the vision recognition module based on the positioning information; The visual recognition module performs multi-view imaging on part i to obtain multiple images of part i; High-performance computers detect part labels from multiple images, calculate label pose, and determine occlusion. The part grasping module adjusts the position of part i to the correct position based on the label pose; The visual recognition module images the label on part i to obtain the label image; A high-performance computer processes the label images, identifies the content of the label images, and retrieves the corresponding assembly relationship guidance mark information from the parts assembly relationship guidance mark database; Iterate through all guide marks of part i, and print guide mark j using the guide mark printer based on the assembly relationship guide mark information; Where j = 1, 2, ..., n, n represents the number of guide marks for part i; The marker pasting module picks up the guide marker j; A high-performance computer plans the pasting path and determines the path solution based on the pose of part i and guide marker j; The marker pasting module pastes guide marker j at the specified position of part i, checks the task progress, and ends the pasting process.

2. The automatic pasting system for guiding the assembly relationship of complex satellite truss parts according to claim 1, characterized in that, The high-performance computer analyzes and calculates point cloud data and label pose using the SGBM stereo matching algorithm, detects part labels using the YOLO target detection algorithm, identifies label image content using the optical character recognition algorithm, and plans the pasting path using the fast exploration random tree algorithm. The multi-view imaging has no fewer than four viewpoints, and the obtained multiple images of part i are no fewer than four. The occlusion determination is to determine whether the label of part i is occluded. If so, the part grasping module puts down part i and repositions part i to change the grasping position. If not, the part grasping module adjusts the pose of part i to the correct position. The position of part i is adjusted so that the normal vector at the center of the part label coincides with the optical axis of the camera lens of the visual recognition module, and is within the depth of field of the visual recognition module. The marker pasting module picks up the guide markers through vacuum adsorption and pastes the guide markers by flexible pressure. The determination of the path solution is to determine whether there is a solution for the pasting path. If there is, the marker pasting module adjusts the pose of the guide marker j; if not, the part grabbing module adjusts the pose of part i and replans the pasting path. The judgment task process is to determine whether all guide marks of part i have been traversed. If not, let a=j, j=a+1, and the guide mark printer continues to print the next guide mark j. If yes, then determine whether all parts of the truss have been traversed. If yes, then end the pasting. If not, let a=i, i=a+1, and the high-performance computer continues to locate the next part i.

3. The automatic pasting system for guiding the assembly relationship of complex satellite truss parts according to claim 1, characterized in that, The high-performance computer includes a host, a monitor, a keyboard, and a mouse, with the host electrically connected to the monitor, keyboard, and mouse respectively. The automatic label pasting control system is electrically connected to a high-performance computer and includes a stereo camera module control circuit, a vision recognition module control circuit, a parts gripping module control circuit, and a label pasting module control circuit, which are electrically connected to the stereo camera module, the vision recognition module, the parts gripping module, and the label pasting module, respectively. The stereo camera module includes an image sensor, a lens, a laser, and a laser galvanometer. The visual recognition module includes an industrial camera, a camera lens, a lighting source, and a mounting bracket; The parts gripping module includes a gripping industrial robotic arm and a gripping end effector; The marking and pasting module includes a marker for an industrial robotic arm and a marker for an end effector. The workbench provides operating space for the parts gripping module and the marking and pasting module.

4. The automatic pasting system for guiding the assembly relationship of complex satellite truss parts according to claim 3, characterized in that, The host's processor has a clock speed of no less than 3.0GHz, memory of no less than 32GB, dedicated graphics card memory of no less than 16GB, and hard drive of no less than 1TB. The display size is not less than 27 inches; The image sensors are used to generate digital images with a resolution of not less than 10 million pixels, and there are no fewer than two of them; The lenses are used to change light, with a field of view of not less than 50°, and their number is consistent with the number of image sensors; The laser is used to generate line lasers, and the number of line lasers is no less than 7. The laser galvanometer is used to scan the surface of the object being measured with a line laser at a frequency of not less than 1 Hz. The industrial cameras are used to generate digital images with a resolution of not less than 10 million pixels, and the number of cameras is not less than four. The camera lens is used to change light, with a field of view of not less than 40°, and the number of lenses is consistent with the number of industrial cameras. The lighting source is a white LED light source, used to illuminate the target; The mounting bracket is used to fix the industrial camera; The gripping industrial robotic arm is a six-degree-of-freedom serial industrial robotic arm with a load of not less than 10kg, used to adjust the position and posture of the gripped part. The gripping end effector has a maximum gripping diameter of not less than Φ100mm and a maximum gripping mass of not less than 6kg, and is used to grip truss parts. The adhesive industrial robotic arm is a six-degree-of-freedom serial industrial robotic arm with a load of not less than 5kg, used to adjust the position and posture of the guide markers; The pasting end effector is used to pick up and paste the guide marker.

5. The automatic pasting system for guiding the assembly relationship of complex satellite truss parts according to claim 3, characterized in that, The high-performance computer is used to set up, manage, and analyze the automatic pasting process of guidance marks for the assembly relationships of complex satellite truss parts; The automatic label pasting control system is used to control the stereo camera module, vision recognition module, parts gripping module, and label pasting module to achieve imaging control, gripping control, and pasting control. The stereo camera module is used to perform laser scanning and multi-view imaging of the parts; The visual recognition module is used to image the parts and their labels; The part gripping module is used to grip and adjust the position of the part; The marker pasting module is used to pick up, adjust the pose of, and paste guide markers; The workbench is used to place truss parts, a high-performance computer and a guide marking printer, and is equipped with a stereo camera module, a vision recognition module, a parts gripping module and a marking and pasting module. The guide mark printer is used to print assembly relationship guide marks that can be pasted; The guide markers are used to display assembly relationship guidance information.

6. A method for automatically pasting assembly relationship guidance marks for complex satellite truss parts, characterized in that, include: Step S1: Analyze the assembly relationships in a high-performance computer based on the 3D model information of the complex satellite truss and the assembly process information; Step S2: Have a high-performance computer generate assembly relationship guidance mark information for all m parts, establish a part assembly relationship guidance mark database, and traverse all m parts; Step S3: The stereo camera module captures point cloud data of part i, where i = 1, 2, ..., m. The high-performance computer analyzes and calculates the point cloud data to locate part i and obtain its positioning information. Step S4: Instruct the part grasping module to grasp part i into the field of view of the vision recognition module based on the positioning information; Step S5: Instruct the visual recognition module to perform multi-view imaging of part i to obtain multiple images of part i; Step S6: Instruct a high-performance computer to detect part labels based on multiple images and calculate the label pose; Step S7: Have the high-performance computer determine the occlusion; Step S8: Instruct the part grasping module to adjust the position of part i to the correct position according to the label pose; Step S9: Instruct the vision recognition module to image the label on part i to obtain the label image; Step S10: Process the label images in a high-performance computer to identify the label image content; Step S11: Instruct the high-performance computer to retrieve the corresponding assembly relationship guidance mark information from the part assembly relationship guidance mark database; Step S12: Let all guide marks of part i be traversed, and the guide mark printer prints guide mark j according to the assembly relationship guide mark information; Where j = 1, 2, ..., n, n represents the number of guide marks for part i; Step S13: Instruct the marker pasting module to pick up the guide marker j; Step S14: Instruct the high-performance computer to plan the pasting path and determine the path solution based on the pose of part i and guide marker j; Step S15: Instruct the marker pasting module to paste the guide marker j at the specified position of part i; Step S16: Check the task progress and end the pasting process.

7. The method for automatically pasting assembly relationship guidance marks for complex satellite truss parts according to claim 6, characterized in that, The high-performance computer analyzes and calculates point cloud data and label pose using the SGBM stereo matching algorithm, detects part labels using the YOLO target detection algorithm, identifies label image content using the optical character recognition algorithm, and plans the pasting path using the fast exploration random tree algorithm. The marker pasting module picks up the guide markers through vacuum adsorption and pastes the guide markers by flexible pressure. In step S5, the number of multi-view imaging perspectives is no less than 4, and the number of multiple images of part i obtained is no less than 4. In step S7, it is determined whether the label of part i is obscured. If so, the part grasping module puts down part i and executes step S3. If not, step S8 is executed. In step S8, the part grasping module makes the normal vector at the center of the part label coincide with the optical axis of the camera lens of the visual recognition module, and within the depth of field of the visual recognition module. In step S14, it is determined whether there is a solution for the pasting path. If yes, step S15 is executed. If no, the part grabbing module adjusts the pose of part i and executes step S14 to replan the pasting path. In step S16, it is determined whether all guide marks of part i have been traversed. If not, let a=j, j=a+1, and execute step S12. If yes, it is determined whether all parts of the truss have been traversed. Determine if all parts of the truss have been traversed. If yes, end the pasting process. If not, set a=i, i=a+1, and execute step S3.

8. The method for automatically pasting assembly relationship guidance marks for complex satellite truss parts according to claim 6, characterized in that, The high-performance computer includes a host, a monitor, a keyboard, and a mouse, with the host electrically connected to the monitor, keyboard, and mouse respectively. The automatic label pasting control system is electrically connected to a high-performance computer and includes a stereo camera module control circuit, a vision recognition module control circuit, a parts gripping module control circuit, and a label pasting module control circuit, which are electrically connected to the stereo camera module, vision recognition module, parts gripping module, and label pasting module, respectively. The stereo camera module includes an image sensor, a lens, a laser, and a laser galvanometer. The visual recognition module includes an industrial camera, a camera lens, a lighting source, and a mounting bracket; The parts gripping module includes a gripping industrial robotic arm and a gripping end effector; The marking and pasting module includes a marker for an industrial robotic arm and a marker for an end effector. The workbench provides operating space for the parts gripping module and the marking and pasting module.

9. The method for automatically pasting assembly relationship guidance marks for complex satellite truss parts according to claim 8, characterized in that, The host's processor has a clock speed of no less than 3.0GHz, memory of no less than 32GB, dedicated graphics card memory of no less than 16GB, and hard drive of no less than 1TB. The display size is not less than 27 inches; The image sensors are used to generate digital images with a resolution of not less than 10 million pixels, and there are no fewer than two of them; The lenses are used to change light, with a field of view of not less than 50°, and their number is consistent with the number of image sensors; The laser is used to generate line lasers, and the number of line lasers is no less than 7. The laser galvanometer is used to scan the surface of the object being measured with a line laser at a frequency of not less than 1 Hz. The industrial cameras are used to generate digital images with a resolution of not less than 10 million pixels, and the number of cameras is not less than four. The camera lens is used to change light, with a field of view of not less than 40°, and the number of lenses is consistent with the number of industrial cameras. The lighting source is a white LED light source, used to illuminate the target; The mounting bracket is used to fix the industrial camera; The gripping industrial robotic arm is a six-degree-of-freedom serial industrial robotic arm with a load of not less than 10kg, used to adjust the position and posture of the gripped part. The gripping end effector has a maximum gripping diameter of not less than Φ100mm and a maximum gripping mass of not less than 6kg, and is used to grip truss parts. The adhesive industrial robotic arm is a six-degree-of-freedom serial industrial robotic arm with a load of not less than 5kg, used to adjust the position and posture of the guide markers; The pasting end effector is used to pick up and paste the guide marker.

10. The method for automatically pasting assembly relationship guidance marks for complex satellite truss parts according to claim 8, characterized in that, The high-performance computer is used to set up, manage, and analyze the automatic pasting process of guidance marks for the assembly relationships of complex satellite truss parts; The automatic label pasting control system is used to control the stereo camera module, vision recognition module, parts gripping module, and label pasting module to achieve imaging control, gripping control, and pasting control. The stereo camera module is used to perform laser scanning and multi-view imaging of the parts; The visual recognition module is used to image the parts and their labels; The part gripping module is used to grip and adjust the position of the part; The marker pasting module is used to pick up, adjust the pose of, and paste guide markers; The workbench is used to place truss parts, a high-performance computer and a guide marking printer, and is equipped with a stereo camera module, a vision recognition module, a parts gripping module and a marking and pasting module. The guide mark printer is used to print assembly relationship guide marks that can be pasted; The guide markers are used to display assembly relationship guidance information.

Images