Robot self-adaptive tightening system for seat ring cushion and operation method

Abstract

The invention relates to a seat cushion robot self-adaptive tightening system and an operation method. The system provided by the invention is composed of an integrated industrial personal computer, an AGV mobile platform, a collaborative robot, a tightening end effector, an industrial camera and accessories thereof. The collaborative robot is installed on the AGV mobile platform, the tightening end effector and the industrial camera are installed at the tail end of the AGV mobile platform, and the whole system is controlled by the integrated industrial personal computer. The accurate position of the center of the to-be-tightened bolt can be obtained through a visual identification method in combination with a designed multi-layer screening method; meanwhile, different feeding modes are set according to different pre-tightening conditions, automatic cap searching is achieved, and it is guaranteed that tightening is in place; in addition, the counter-acting force arm is added to counteract counter-acting force in the tightening process, and robot damage is avoided. The tightening system and the operation method provided by the invention not only have extremely high flexibility, but also can adapt to a complex tightening environment, so that the accuracy of tightening work is ensured, and the working efficiency is also improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automated bolt tightening, and in particular to a seat washer robot adaptive tightening system and an operating method. Background Art

[0002] With the continuous development and maturity of robots and related technologies, as well as the rising labor costs, robots are playing an increasingly important role in production. A large number of factories have begun to invest in robots to cooperate with manual labor in production operations, which can improve work efficiency.

[0003] Bolt tightening is a very important part of mechanical assembly. It has been done manually for a long time. For some large equipment, there are hundreds of bolts that need to be tightened, and the manual production efficiency will be very low. In order to improve production efficiency and reduce the labor intensity of workers, many production solutions that use mechanical equipment instead of manual labor have emerged in recent years.

[0004] The patent "CN 119175678 A, a nut storage and supply device for automatic tightening" integrates nut storage, supply and automatic tightening. By storing nuts in a nut cache and then feeding the nuts from the nut cache into the nut sleeve of the tightening shaft at one time, the tightening shaft automatically removes the next nut directly after tightening a nut and then tightens it at the next position, so that the nut tightening can be carried out automatically and continuously. However, the device itself cannot move, and other equipment is required to transport the workpiece to be tightened to the bottom of the nut sleeve, which is not suitable for large equipment. The patent "CN 108608200 A, tightening control management system and tightening control method" provides a tightening control management system and a tightening control method, which uses RFID radio frequency identification technology to realize local control of the tightening control management system, so that the system can run off the network to improve the stability and reliability of the system. This method has high application value, but it needs to read all pre-set parameters and cannot be adjusted according to actual conditions.

[0005] Existing automatic tightening solutions are mostly targeted at specific production environments, with poor versatility, and the tightening devices are fixed and cannot be flexibly moved. The tightening system proposed in the present invention uses the AGV mobile platform and the collaborative robot as carriers, can move over a large range in the production environment, and achieve high-torque tightening in a small space. At the same time, the operating method designed for the system proposed in the present invention makes corresponding adjustments to different pre-tightening conditions during the specific operation process, and has better environmental adaptability and flexibility. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention proposes a seat ring gasket robot adaptive tightening system and operation method, aiming to solve the problems of low manual production efficiency and high workload of workers, and utilize the characteristics of collaborative robots to improve the flexibility and versatility of the tightening device.

[0007] In order to achieve the above technical objectives, the present invention proposes a seat ring gasket robot adaptive tightening system, which specifically includes:

[0008] AGV mobile platform, collaborative robot, tightening end effector, industrial camera and its accessories, and all-in-one industrial computer;

[0009] A collaborative robot is fixedly installed above the AGV mobile platform; the bottom surface of the collaborative robot is parallel to the horizontal ground, and a tightening end effector, an industrial camera and accessories are installed at its end through a plate-shaped connecting piece; the tightening end effector is rotatably connected to the plate-shaped connecting piece through a bearing, and the industrial camera and accessories are fixed to the plate-shaped connecting piece through screws; all components are connected to an integrated industrial computer;

[0010] The AGV mobile platform is used to drive the collaborative robot to move; the collaborative robot is used to drive the tightening end effector, industrial camera and accessories to reach the designated position and perform operations according to the planned route; the tightening end effector is used to perform tightening operations in a narrow space; the industrial camera and accessories are used to collect image data and position data of the parts to be tightened; the integrated industrial computer is used to process data, plan paths, and control the movement and operation of each component.

[0011] Furthermore, the tightening end effector comprises:

[0012] Tightening guns, sockets, cylinders, reaction arms, small Z-shaped connectors and cube-shaped connectors;

[0013] The cubic connector is composed of a top plate, two side plates, and a bottom plate. The plates are connected by screws. The top plate is connected to the bearing of the plate-shaped connector by a circular structure. The two side plates are connected to the bottom plate. The tightening gun is inserted through the surface without the side plates and is fixed to the bottom plate by screws. The bottom plate has a circular hollow for the end of the tightening gun to extend. The sleeve is fixed to the end of the tightening gun by an adapter and screws and rotates with the end of the tightening gun. The reaction force arm is welded to the bottom plate.

[0014] The inner cavity of the sleeve is designed to be a regular hexagonal structure similar to that of the bolt cap, and the inner cavity area is slightly larger than that of the bolt cap; when the bolt cap is inserted into the sleeve and tightened, the two rotate simultaneously and do not rotate relative to each other; a spring is connected to the end of the sleeve, and when subjected to an axial force, it is adaptively compressed along the axial direction of the sleeve to avoid rigid collision between the sleeve and the bolt surface and the mounting surface during axial feeding;

[0015] One end of the cylinder is hinged on the plate-like connector, and the other end is hinged to the small Z-shaped connector; the small Z-shaped connector is fixedly connected to the top plate of the cube-shaped connector by screws, and the small Z-shaped connector converts the linear motion of the cylinder extension and contraction into the rotation of the cube-shaped connector, thereby promoting the extension and retraction of the reaction force arm; the reaction force arm is used to balance the reaction force of the bolt nut on the end of the collaborative robot during tightening operations.

[0016] Furthermore, the industrial camera and accessories include:

[0017] Camera, light source, laser displacement sensor;

[0018] The camera and the laser displacement sensor are installed adjacent to each other on a plate-like connecting piece, and the laser displacement sensor is kept level with the camera during installation to ensure that the height of the camera is the same each time it takes a picture; the light source is installed around the lens of the camera in a circular ring shape; the camera, light source, and laser displacement sensor maintain a certain height difference with the sleeve during installation to avoid collision with the installation platform.

[0019] The present invention also provides a seat ring gasket robot adaptive tightening system, which specifically includes the following steps:

[0020] S1. Build a seat pad robot adaptive tightening system; fix the tightening end effector, industrial camera and its accessories at the end of the collaborative robot, and connect the collaborative robot to the AGV mobile platform, with its bottom surface parallel to the horizontal ground;

[0021] The tightening end effector includes a tightening gun, a sleeve, a cylinder, and a reaction force arm; the industrial camera and its accessories include a camera, a light source, and a laser displacement sensor;

[0022] All components are connected to and controlled by an integrated industrial computer;

[0023] S2. Establish the coordinate systems of each part of the system, including: AGV mobile platform coordinate system, robot base coordinate system, robot end coordinate system, camera coordinate system, sleeve coordinate system, installation workpiece coordinate system, and determine the relative position relationship between the coordinate systems of each part;

[0024] S3, perform hand-eye calibration and tighten end effector calibration; determine the relative position relationship between the camera and the sleeve through hand-eye calibration, obtain the transformation matrix of the camera coordinate system relative to the robot end coordinate system, and obtain the transformation matrix of the sleeve coordinate system relative to the robot end coordinate system through tightening end effector calibration;

[0025] S4, teaching the photographing points and setting the photographing parameters; through manual teaching, ensure that the bolt to be tightened is located at the center of the camera's field of view, and after ensuring that a clear and identifiable image of the bolt to be tightened without ghosting or blurring can be taken, record the position information and photographing parameters of the end of the collaborative robot in the robot base coordinate system, and after obtaining the photographing point of a bolt to be tightened, calculate the photographing points of the remaining bolts to be tightened based on the product digital model information; setting the photographing parameters includes setting the exposure time and gain;

[0026] S5, perform path planning and offline programming; according to the photographing points of the bolts to be tightened obtained in step S4, the product digital model information, and the relative positions of the entire tightening system and the system to be tightened, plan the motion path of the collaborative robot to ensure the highest tightening efficiency, and use offline programming to ensure that the collaborative robot can run in an offline state to reach each photographing point, completing the entire path planning and offline programming workflow;

[0027] S6. Set the process parameters of the tightening gun according to the actual working conditions to meet the tightening requirements;

[0028] S7. Based on the different pre-tightening states of the bolts, each photographing point obtained in step S4 is corrected; the collaborative robot first moves according to the path preset by offline programming, and after reaching each photographing point, a laser displacement sensor is used to ensure that the height from the camera to the upper surface of each bolt cap remains unchanged, thereby correcting each photographing point;

[0029] S8, identifying the center position of the bolt to be tightened; after the end of the collaborative robot reaches the corrected photo-taking point, the camera is started to take a photo, and the image is transmitted to the integrated industrial computer. The obtained image is identified and processed using the preset algorithm program in the integrated industrial computer. By designing a multi-layer screening method, the precise position of the center of each bolt to be tightened in the robot base coordinate system is obtained;

[0030] S9, the end of the collaborative robot moves to the precise position obtained in step S8, runs the cap-finding program, controls the bolt cap to be inserted into the sleeve, the cylinder pushes the reaction force arm to extend, against the installation workpiece, the tightening gun starts tightening, and the bolt rotates with the sleeve until the tightening reaches the torque set by the processing task to complete the tightening;

[0031] S10. After the bolt is tightened, the cylinder works, the reaction force arm retracts, and the sleeve first rotates slightly in the opposite direction of tightening to create a gap between its inner cavity and the side surface of the bolt cap, and then the end moves in the vertical direction to separate the sleeve and the bolt;

[0032] S11. The integrated industrial computer makes a judgment. If there are still bolts to be tightened, steps S7-S10 are repeated until all tightening tasks are completed; if all tightening tasks have been completed, the system returns to the initial position.

[0033] Based on the above technical solution, the present invention has at least the following beneficial effects:

[0034] 1) The present invention adopts a collaborative robot as a carrier of the tightening device, which has a small size and is installed on an AGV mobile platform. It has high flexibility, can achieve a large range of movement, and can adapt to complex working environments.

[0035] 2) The present invention designs a lightweight and automated tightening end effector, which can be mounted on a small collaborative robot and can realize tightening operations in a narrow space. In addition, a reaction force arm is added to the tightening end effector to offset the reaction force during the tightening process and avoid damage to the robot caused by the reaction force.

[0036] 3) The present invention adopts a visual recognition method, utilizes a laser displacement sensor, and combines a designed multi-layer screening method to achieve high-precision recognition of the center of the bolt nut to be tightened under different pre-tightening states, thereby guiding the end of the collaborative robot to accurately position itself at the position to be tightened.

[0037] 4) The present invention designs a compressible sleeve, which improves the adaptability to the bolt tightening requirements under different pre-tightening states, and designs corresponding tightening feeding schemes for the bolts under different pre-tightening states, which can realize automatic and continuous tightening with high tightening efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic diagram of the overall structure of the system proposed by the present invention;

[0039] Figure 2 A specific structural diagram of the tightening end effector, the industrial camera and its accessories in the system proposed by the present invention;

[0040] Figure 3 A flowchart of the operating method of the system proposed by the present invention;

[0041] Figure 4 This is a flow chart of bolt center position identification in the operation method proposed by the present invention;

[0042] Figure numbers: 1-AGV mobile platform, 2-collaborative robot, 3-tightening end effector, 4-industrial camera and its accessories; 301-tightening gun, 302-sleeve, 303-cylinder, 304-reaction arm; 401-industrial camera, 402-light source, 403-laser displacement sensor. DETAILED DESCRIPTION

[0043] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0044] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following will be combined with the attached Figure 1-4 The present invention is described in detail. It should be noted that these specific embodiments are only used to explain the present invention and do not limit its scope. In addition, the technical features involved in each embodiment described in the text can be combined with each other as long as they do not conflict with each other.

[0045] When describing the present invention, it should be particularly noted that, unless otherwise expressly specified or limited, when a component is mentioned to be "connected" to another component, it means that it can be directly connected or indirectly connected through an intermediate medium. Terms such as "installation" and "fixed" should be understood broadly. For example, they can refer to fixed connection, detachable connection or integral connection, mechanical connection or electrical connection, direct connection or indirect connection through an intermediate, and even include the internal connection relationship or interaction between two components. For ordinary technicians in this field, the specific meanings of these terms in the present invention can be understood according to specific circumstances.

[0046] In addition, although the steps in the present invention are arranged with numbers, they are not used to limit the order of the steps. Unless the order of the steps is clearly stated or the execution of a certain step requires other steps as a basis, the relative order of the steps can be adjusted. It is understood that the term "and / or" used in this article involves and covers any and all possible combinations of one or more of the associated listed items.

[0047] like Figure 1 As shown, the present invention proposes a seat ring gasket robot adaptive tightening system, which specifically includes:

[0048] AGV mobile platform 1, collaborative robot 2, tightening end effector 3, industrial camera and its accessories 4, and integrated industrial computer;

[0049] A collaborative robot 2 is fixedly installed above the AGV mobile platform 1; the bottom surface of the collaborative robot 2 is parallel to the horizontal ground, and a tightening end effector 3 and an industrial camera and accessories 4 are installed at its end through a plate-shaped connecting piece; the tightening end effector 3 is rotatably connected to the plate-shaped connecting piece through a bearing, and the industrial camera and accessories 4 are fixed to the plate-shaped connecting piece through screws; all components are connected to an integrated industrial computer;

[0050] The AGV mobile platform 1 is used to drive the collaborative robot 2 to move; the collaborative robot 2 is used to drive the tightening end effector 3 and the industrial camera and accessories 4 to reach the designated position and perform operations according to the planned route; the tightening end effector 3 is used to perform tightening operations in a narrow space; the industrial camera and accessories 4 are used to collect image data and position data of the parts to be tightened; the integrated industrial computer is used to process data, plan paths, and control the movement and operation of each component.

[0051] In this embodiment, the tightening end effector 3 and the industrial camera and accessories 4 are collectively referred to as the robot end effector, which will move with the end of the collaborative robot 2. The specific structures of these two components are as follows: Figure 2 As shown:

[0052] The tightening end effector 3 comprises: a tightening gun 301, a sleeve 302, a cylinder 303, a reaction force arm 304, a small Z-shaped connector and a cubic connector;

[0053] The cubic connector is composed of a top plate, two side plates, and a bottom plate. The plates are connected by screws. The top plate is connected to the bearing of the plate-shaped connector by a circular structure. The two side plates are connected to the bottom plate. The tightening gun 301 is inserted through the surface without side plates and fixed to the bottom plate by screws. The bottom plate has a circular hollow for the end of the tightening gun 301 to extend. The sleeve 302 is fixed to the end of the tightening gun 301 by an adapter and screws, and rotates with the end of the tightening gun 301. The reaction force arm 304 is welded to the bottom plate.

[0054] The inner cavity of the sleeve 302 is designed to be a regular hexagonal structure similar to that of the bolt cap, and the inner cavity area is slightly larger than that of the bolt cap; when the bolt cap is inserted into the sleeve 302 and tightened, the two rotate simultaneously and do not rotate relative to each other; a spring is connected to the end of the sleeve 302, which is adaptively compressed along the axial direction of the sleeve 302 when subjected to axial force, so as to avoid rigid collision between the sleeve 302 and the bolt surface and the mounting surface during axial feeding; in addition, it should be noted that the bolt cap in this application refers to the regular hexagonal head at the top of the bolt.

[0055] One end of the cylinder is hinged on the plate-like connector, and the other end is hinged to the small Z-shaped connector; the small Z-shaped connector is fixedly connected to the top plate of the cube-shaped connector by screws, and the small Z-shaped connector converts the linear motion of the cylinder extension and contraction into the rotation of the cube-shaped connector, thereby promoting the extension and retraction of the reaction force arm; the reaction force arm is used to balance the reaction force of the bolt nut on the end of the collaborative robot during tightening operations.

[0056] The industrial camera and accessories 4 include: a camera 401, a light source 402, and a laser displacement sensor 403;

[0057] The camera 401 and the laser displacement sensor 403 are installed adjacent to each other on a plate-like connecting piece, and the laser displacement sensor 403 is kept level with the camera 401 when installed, so as to ensure that the height of the camera 401 is the same every time it takes a picture; the light source 402 is installed around the lens of the camera 401 in a circular shape; the camera 401, the light source 402, and the laser displacement sensor 403 maintain a certain height difference with the sleeve 302 when installed to avoid collision with the installation platform.

[0058] like Figure 3-4As shown, an operation method of a seat ring gasket robot adaptive tightening system proposed by the present invention is shown, which specifically includes the following steps:

[0059] S1. Build a seat pad robot adaptive tightening system; fix the tightening end effector 3, the industrial camera and its accessories 4 at the end of the collaborative robot 2, and connect the collaborative robot 2 to the AGV mobile platform 1, and its bottom surface is parallel to the horizontal ground;

[0060] The tightening end effector 3 includes a tightening gun 301, a sleeve 302, a cylinder 303, and a reaction force arm 304; the industrial camera and its accessories include a camera 401, a light source 402, and a laser displacement sensor 403;

[0061] All components are connected to and controlled by an integrated industrial computer;

[0062] It should also be noted that, in this embodiment, the bolts to be tightened and the installation workpiece also constitute a system to be tightened.

[0063] S2. Establish the coordinate systems of each part of the system, including: AGV mobile platform coordinate system, robot base coordinate system, robot end coordinate system, camera coordinate system, sleeve coordinate system, installation workpiece coordinate system, and determine the relative position relationship between the coordinate systems of each part;

[0064] S3, perform hand-eye calibration and tightening end effector calibration; determine the relative position relationship between the camera 301 and the sleeve 302 through hand-eye calibration, and obtain the transformation matrix of the camera coordinate system relative to the robot end coordinate system, and obtain the transformation matrix of the sleeve coordinate system relative to the robot end coordinate system through tightening end effector calibration; in this embodiment, steps S2-S3 establish the coordinate system and perform calibration in order to accurately locate the bolts to be tightened and accurately guide the movement of the end of the collaborative robot 2

[0065] S4, teaching the photographing point and setting the photographing parameters; through manual teaching, ensure that the bolt to be tightened is located at the center of the field of view of the camera 401, and after ensuring that a clear and identifiable image of the bolt to be tightened without ghosting or blurring can be taken, record the posture information and photographing parameters of the end of the collaborative robot 2 in the robot base coordinate system, and after obtaining the photographing point of a bolt to be tightened, calculate the photographing points of the remaining bolts to be tightened based on the product digital model information; setting the photographing parameters includes setting the exposure time and gain;

[0066] S5, perform path planning and offline programming; according to the photographing points of the bolts to be tightened obtained in step S4, the product digital model information, and the relative positions of the entire tightening system and the system to be tightened, plan the movement path of the collaborative robot 2 to ensure the highest tightening efficiency, and use offline programming to ensure that the collaborative robot 2 can run in an offline state to reach each photographing point, completing the entire path planning and offline programming workflow;

[0067] S6. Set the process parameters of the tightening gun 301 according to the actual working conditions to meet the tightening requirements. So far, steps S1-S6 have completed the preparation process of the tightening operation. Now start the tightening operation.

[0068] S7, based on the different pre-tightening states of each bolt, each photographing point obtained in step S4 is corrected; the collaborative robot 2 first moves according to the path preset by offline programming, and after reaching each photographing point, the laser displacement sensor 403 is used to ensure that the height from the camera 401 to the upper surface of each bolt cap remains unchanged, so as to realize the correction of each photographing point;

[0069] As a preferred embodiment, in step S7, the laser displacement sensor 403 is used to ensure that the height from the camera 401 to the upper surface of each bolt cap remains unchanged, and the correction of each photographing point is realized specifically as follows:

[0070] The preset height from the camera 401 to the upper surface of the bolt cap is set to h0, and the default height at which the end moves to each photographing point for photographing is H. The actual height h from the camera 401 to the upper surface of the bolt cap varies due to the different pre-tightening states of each bolt to be tightened. In order to facilitate subsequent image processing, in this embodiment, the laser displacement sensor 403 is used to measure the value of the actual height h, and each photographing point is corrected according to the difference between the actual height h and h0; the formula is expressed as:

[0071]

[0072] Wherein, H' represents the corrected height at which the end point moves to each photographing point for taking photos.

[0073] S8, identifying the center position of the bolt to be tightened; after the end of the collaborative robot 2 reaches the corrected photographing point, the camera 401 is started to take a photo, and the image is transmitted to the integrated industrial computer. The obtained image is identified and processed using the algorithm program preset in the integrated industrial computer. By designing a multi-layer screening method, the precise position of the center of each bolt to be tightened in the robot base coordinate system is obtained;

[0074] As a preferred embodiment, Figure 4 As shown, step S8 specifically includes:

[0075] S81. The bolt to be tightened is a hexagonal head, and its top view consists of a regular hexagon and the inscribed circle of the hexagon. First, the image obtained at the current shooting point is processed in the image coordinate system. Since the distances between the several bolts to be tightened are relatively close, the obtained image may include the top views of multiple bolts. Therefore, the inscribed circle of the bolt to be tightened at the current shooting point is identified through multi-layer screening to obtain the center data. In this embodiment, the image coordinate system refers to a plane coordinate system with the upper left corner of the image taken as the coordinate origin, the x-axis parallel to the image plane horizontally to the right, and the y-axis parallel to the image plane perpendicular to the x-axis downward;

[0076] More specifically, step S81 specifically includes:

[0077] S811. First, the fitting ellipses of all the bolts in the image are obtained. Since all the bolt images are taken at a fixed height, the circumference and area of ​​the inscribed circle of each bolt are similar. Therefore, the fitting ellipses are first screened based on their circumference and area according to the following formula:

[0078]

[0079] Among them, S and C are the area and perimeter of the ellipse currently involved in the first-level screening and fitting, respectively. MIN , S MAX , C MIN , C MAX They represent the minimum and maximum values ​​of the area of ​​the fitted ellipse and the minimum and maximum values ​​of the perimeter of the fitted ellipse that meet the set conditions. Considering that the ambient light will change and the surface conditions of each bolt are different, the range of the area and perimeter should not be too small in actual selection.

[0080] S812. After the first level of screening is completed, most of the ellipses that do not meet the conditions are screened out. At this time, the second level of screening is performed, and two fitting ellipses are selected from the remaining fitting ellipses after the first level of screening to calculate the center distance between the two fitting ellipses to avoid the existence of two ellipses whose centers are too close to each other; for the two fitting ellipses whose center distance is too close, only one of them is selected to be retained; that is:

[0081] First calculate the center distance L of the two fitting ellipses, the formula is expressed as:

[0082]

[0083] Among them, (x m ,y m ), (x n ,y n ) represents the coordinates of the centers of the two fitted ellipses involved in the calculation in the image coordinate system;

[0084] Then compare it with the maximum value L0 of the center distance between the two fitted ellipses to decide whether to filter out one of the fitted ellipses. The formula is:

[0085]

[0086] The remaining fitted ellipses after the second level of screening meet the perimeter and area requirements, and there are no other fitted ellipse centers near their centers;

[0087] S813, perform the third level screening, and perform roundness screening on the remaining fitted ellipses after the second level screening, and the formula is expressed as:

[0088]

[0089] Wherein, a represents the length of the semi-major axis of the fitting ellipse, b represents the length of the semi-minor axis of the fitting ellipse, and R0 represents the set roundness requirement, and its value ranges from 0 to 1. In order to ensure that the retained fitting ellipse is close to the inscribed circle, in this embodiment, R0 takes a value close to 1. At the same time, due to the existence of the second layer of screening, there is only one fitting ellipse that meets the roundness requirement (the ellipse with similar roundness has a similar ellipse center and is discarded). Finally, the retained fitting ellipse is used as the inscribed circle of the bolt.

[0090] S814. After the above three levels of screening, the inscribed circles of all bolts in the image are screened out, and then the one with the center of the inscribed circle closest to the center of the image is screened out as the inscribed circle of the bolt to be tightened at the current photographing point; specifically:

[0091] First calculate the coordinates of the center of the image (x0, y0), the formula is:

[0092]

[0093] Where W represents the width of the image and H represents the height of the image;

[0094] Then calculate the distance from the center of each inscribed circle to the center of the image, and find the shortest distance. The formula is:

[0095]

[0096] L Cmin =min{L Ci |i∈[1,2,...,n]};

[0097] Among them, L Ci represents the distance from the center of the i-th inscribed circle to the center of the image, L Cmin It represents the shortest distance from the center of the image. The center coordinates of the circle corresponding to this distance are the coordinates of the center of the inscribed circle of the bolt to be tightened at the current shooting point in the image coordinate system, recorded as (xc0 ,y c0 ).

[0098] S82, delineate a ROI (region of interest) with the center of the circle as the center, the ROI excludes other irrelevant parts in the image, and only leaves the bolt to be tightened at the current photographing point; then screen the six sides of the regular hexagon, and after the six sides are screened, obtain the six intersection points of the six sides as the six corner points of the regular hexagon; take the average of the coordinates of the six points as the precise position of the center of the bolt to be tightened at the current photographing point in the image coordinate system, and then transform the precise position of the center of the bolt to be tightened at the current photographing point in the robot base coordinate system through the positional relationship between the coordinate systems;

[0099] Step S82 specifically includes:

[0100] S821, taking the inscribed circle center of the bolt to be tightened at the current photographing point as the center and the entire hexagonal rectangular area including the projection of the bolt cap as the ROI area; and filtering out all line segments in the ROI area from the image, the formula is expressed as:

[0101]

[0102] Among them, W R and H R Indicates the width and height of the ROI area, (x A ,y A ) and (x B ,y B ) represent the two endpoints of the line segment respectively;

[0103] S822, after all line segments in the ROI area are screened out, line segments that are judged to be repeated are screened out according to the cosine values ​​and midpoint distances between the line segments, and are divided into six groups; specifically:

[0104] First calculate the cosine between the two line segments When the cosine value satisfies When , the two line segments are parallel, and the two line segments are considered to be repeated and classified into the same group;

[0105] Among them, P represents the minimum cosine value for determining whether two straight lines are parallel, A and B represent the vectors corresponding to the two line segments; |A| and |B| are the moduli of the two vectors;

[0106] Then, the midpoint distance is used to filter out the cases where the sides are parallel because they are opposite sides of the hexagon; the formula is expressed as:

[0107]

[0108] Among them, (x 1a ,y 1a )、(x1b ,y 1b )、(x 1c ,y 1c ) represent the coordinates of the two endpoints and the midpoint of line segment 1, respectively. (x 2a ,y 2a )、(x 2b ,y 2b )、(x 2c ,y 2c ) represent the coordinates of the two endpoints and the midpoint of line segment 2 respectively, and line segment 1 and line segment 2 are judged to be parallel; L c0 Indicates the maximum value of the distance between the midpoints of the two line segments. When the distance between the midpoints of the two line segments does not exceed L c0 , then keep the judgment that these two line segments are repeated;

[0109] After judging the cosine value and midpoint distance, six groups of line segments are obtained, and each line segment in the group is judged to be repeated;

[0110] S823. According to the distance from the midpoint of the line segment to the center of the inscribed circle, select the line segment representing each side of the regular hexagon from each group. The formula is:

[0111]

[0112] Among them, l 1c , l 2c They represent the distances from the center of line segment 1 and line segment 2 in a group to the center of the inscribed circle. Each time, the line segment with the longest distance to the center of the inscribed circle is retained. After all the line segments in the group are traversed, the last line segment retained represents one side of the regular hexagon. After all six groups are screened, six line segments representing the six sides of the regular hexagon are obtained.

[0113] S824. According to the straight line equations of the six line segments obtained in step S823, the intersection points where the six straight lines intersect each other are obtained. The formula is:

[0114] The general equation of the straight line on which each of the six line segments lies: A i x+B i y+C i =0(i=1,2,...,6);

[0115] Intersection calculation formula: i,j=1,2,...,6,i≠j;

[0116] Among them, A i , B i , C i are the coefficients of the general equation of line i, A j , B j , C j are the coefficients of the general equation of line j, (xij ,y ij ) is the intersection point of lines i and j

[0117] Then, based on the fact that the distance from the intersection of non-adjacent straight lines to the center of the inscribed circle is greater than the distance from the intersection of adjacent straight lines to the center of the inscribed circle, non-adjacent straight line intersections are screened out. The formula is:

[0118]

[0119] Among them, L c1 is the set distance threshold, exceeding the distance threshold L c1 The intersection points are considered as non-adjacent straight line intersection points and are discarded; the six intersection points retained after final screening are the six corner points of the regular hexagon, and the six corner points are recorded as x n ,n=1,2,...,6;

[0120] S825, calculate the coordinates (x c ,y c ):

[0121]

[0122] Convert the image coordinate system to the robot base coordinate system according to (x c ,y c ) calculates the precise position of the center of the bolt to be tightened at the current photographing point in the robot base coordinate system, and then guides the end of the collaborative robot 2 to move to the exact position for tightening.

[0123] S83, traverse each corrected photographing point, repeat steps S81-S82, and obtain the precise position of the center of each bolt to be tightened in the base coordinate system.

[0124] S9, the end of the collaborative robot 2 moves to the precise position obtained in step S8, runs the cap-finding program, controls the bolt cap to be inserted into the sleeve 302, and the cylinder 303 pushes the reaction force arm 304 to extend and resist the installation workpiece, and the tightening gun 301 starts tightening, and the bolt rotates with the sleeve 302 until the tightening reaches the torque set by the processing task to complete the tightening;

[0125] As a preferred implementation, step S9 specifically includes:

[0126] S91. According to the precise position obtained in step S8, the end of the collaborative robot 2 first moves in the horizontal direction until the axis of the bolt is in line with the axis of the sleeve 302, and then the end is fed axially as a whole, and the sleeve 302 approaches the surface of the bolt. Different feeding and tightening methods are required according to the different pre-tightening states of each bolt to be tightened; the formula is expressed as:

[0127]

[0128] Wherein, h is the height of the camera 401 relative to the upper surface of the bolt cap obtained by the laser displacement sensor 403 before the photographing height adjustment, and h0 is the photographing height;

[0129] S92, when h≥h0, the bolt has been pre-tightened in place and one-time feeding is adopted; specifically:

[0130] First, the cap is searched, and the end of collaborative robot 2 feeds h0-h along the axial direction. t +h l , where h t represents the axial distance difference between the lower surface of the sleeve 302 and the camera 401, h l Indicates the thickness of the bolt cap;

[0131] After the feeding is completed, if the bolt is not inserted into the sleeve 302, but the lower surface of the sleeve 302 contacts the upper surface of the bolt, the feeding cannot continue. At this time, the spring is compressed by force, and the compression amount is h l , the sleeve 302 is controlled by the tightening gun 301 to move at a lower angular velocity w l After slowly rotating for one circle, when the inner cavity of the sleeve 302 and the shape of the bolt cap completely coincide, the bolt cap is inserted into the sleeve 302 under the elastic force of the spring, and the bolt cap is found as the sleeve 302 rotates;

[0132] After the cap search is completed, the reaction arm 304 is pushed out by the cylinder 303 to press against the edge of the installation workpiece, and the tightening gun 301 controls the sleeve 302 to move at a higher angular velocity w h Rotate to tighten the bolts; when the tightening torque reaches the task requirement, the tightening is completed;

[0133] S93, when h<h0, the bolt is not pre-tightened in place, and the distance between the upper surface of the bolt and the installation workpiece is h0+h l -h, when tightening, the total axial feed of the end of collaborative robot 2 increases by h0-h compared with the case of one-time feeding. In this case, multiple feeding is adopted, specifically:

[0134] First, the end of collaborative robot 2 still feeds h0-h along the axial direction t +h l , and perform the same cap-finding operation as the tightening process of one feed; after the cap-finding is completed, the lower surface of the sleeve 302 is h0-h away from the installation workpiece, then the end of the collaborative robot 2 is controlled to feed downward again h0-h, the bolt is inserted into the inner cavity of the sleeve 302, and the lower surface of the sleeve 302 fits the installation workpiece; then, the cylinder 303 pushes the reaction force arm 304 to extend and press against the edge of the installation workpiece, and the tightening gun 301 controls the sleeve to move at a higher angular velocity w hRotate to tighten the bolt, and when the tightening torque reaches the task requirement, the tightening is completed.

[0135] In this embodiment, the working principle of the reaction force arm 304 provided in the present invention is also given: when further tightening the bolt after pre-tightening, the sleeve 302 will be subjected to a large torque T1 opposite to the tightening direction, and the sleeve 302 is installed at the end of the collaborative robot 2. The torque will eventually act on the collaborative robot 2 body, increasing the load on each axis of the robot. When the torque is too large, it will trigger the collaborative robot 2 to stop urgently. When working continuously, it will be under a high load for a long time, which will affect the service life of the robot. Therefore, the reaction force arm is designed to balance the torque. During the tightening process, the cylinder pushes the reaction force arm to extend and press against the side of the mounting table. The mounting table provides a support force F2 for the force arm, forming a balanced torque opposite to T1, reducing the load on the robot body and ensuring the stability of the operation.

[0136] S10, after the bolt is tightened, the cylinder 303 works, the reaction force arm 304 retracts, and the sleeve 302 first rotates slightly in the opposite direction of tightening to create a gap between its inner cavity and the side surface of the bolt cap, and then the end moves in the vertical direction to separate the sleeve 302 from the bolt;

[0137] S11. The integrated industrial computer makes a judgment. If there are still bolts to be tightened, steps S7-S10 are repeated until all tightening tasks are completed; if all tightening tasks have been completed, the system returns to the initial position.

[0138] So far, the tightening system proposed by the present invention has completed the entire tightening operation according to the above operation method. In summary, the seat ring pad robot adaptive tightening system and operation method proposed by the present invention have extremely high flexibility and can adapt to complex tightening environments, which not only ensures the accuracy of the tightening work, but also improves the work efficiency.

[0139] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0140] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A seat ring gasket robot adaptive tightening system, characterized in that: Specifically include: AGV mobile platform (1), collaborative robot (2), tightening end effector (3), industrial camera and its accessories (4), and integrated industrial computer; A collaborative robot (2) is fixedly mounted above the AGV mobile platform (1); the bottom surface of the collaborative robot (2) is parallel to the horizontal ground, and a tightening end effector (3) and an industrial camera and accessories (4) are mounted on the end of the collaborative robot via a plate-shaped connecting piece; the tightening end effector (3) is rotatably connected to the plate-shaped connecting piece via a bearing, and the industrial camera and accessories (4) are fixed to the plate-shaped connecting piece via screws; all components are connected to an integrated industrial computer; The AGV mobile platform (1) is used to drive the collaborative robot (2) to move; the collaborative robot (2) is used to drive the tightening end effector (3) and the industrial camera and accessories (4) to reach a designated position and perform operations according to a planned route; the tightening end effector (3) is used to perform tightening operations in a narrow space; the industrial camera and accessories (4) are used to collect image data and position data of the parts to be tightened; The integrated industrial computer is used to process data, plan paths, and control the movement and operation of various components.

2. The seat ring gasket robot adaptive tightening system according to claim 1, characterized in that: The tightening end effector (3) comprises: A tightening gun (301), a sleeve (302), a cylinder (303), a reaction force arm (304), a small Z-shaped connecting piece and a cubic connecting piece; The cubic connector is composed of a top plate, two side plates, and a bottom plate. The plates are connected by screws. The top plate is connected to the bearing of the plate-shaped connector by a circular structure. The two side plates are connected to the bottom plate. The tightening gun (301) extends through the surface without the side plates and is fixed to the bottom plate by screws. The bottom plate has a circular hollow for the end of the tightening gun (301) to extend. The sleeve (302) is fixed to the end of the tightening gun (301) by an adapter and screws and rotates with the end of the tightening gun (301); the reaction force arm (304) is welded to the bottom plate; The inner cavity of the sleeve (302) is designed to have the same regular hexagonal structure as the bolt cap, and the inner cavity area is slightly larger than the bolt cap; when the bolt cap is inserted into the sleeve (302) and tightened, the two rotate simultaneously and do not rotate relative to each other; the end of the sleeve (302) is connected to a spring, which is adaptively compressed along the axial direction of the sleeve (302) when subjected to an axial force, so as to avoid rigid collision between the sleeve (302) and the bolt surface and the mounting surface during axial feeding; One end of the cylinder (303) is hinged on the plate-shaped connector, and the other end is hinged to the small Z-shaped connector; the small Z-shaped connector is fixedly connected to the top plate of the cube-shaped connector by screws, and the small Z-shaped connector converts the linear motion of the cylinder (303) to the rotation of the cube-shaped connector, thereby promoting the extension and retraction of the reaction force arm (304); the reaction force arm (304) is used to balance the reaction force of the bolt nut on the end of the collaborative robot (2) during the tightening operation.

3. The seat ring gasket robot adaptive tightening system according to claim 2, characterized in that: The industrial camera and accessories (4) include: Camera (401), light source (402), laser displacement sensor (403); The camera (401) and the laser displacement sensor (403) are installed adjacent to each other on a plate-shaped connecting member, and the laser displacement sensor (403) is kept horizontal with the camera (401) when installed, so as to ensure that the height of the camera (401) is the same each time it takes a picture; the light source (402) is installed around the lens of the camera (401) in a circular ring shape; the camera (401), the light source (402), and the laser displacement sensor (403) maintain a certain height difference with the sleeve (302) when installed, so as to avoid collision with the installation platform.

4. A method for operating a seat washer robot adaptive tightening system, characterized in that: The specific steps include: S1. Build a seat ring gasket robot adaptive tightening system; fix the tightening end effector (3), industrial camera and its accessories (4) at the end of the collaborative robot (2), and fix the collaborative robot (2) on the AGV mobile platform (1), and its bottom surface is parallel to the horizontal ground; The tightening end effector (3) comprises a tightening gun (301), a sleeve (302), a cylinder (303), and a reaction force arm (304); the industrial camera and its accessories comprise a camera (401), a light source (402), and a laser displacement sensor (403); All components are connected to and controlled by an integrated industrial computer; S2. Establish the coordinate systems of each part of the system, including: AGV mobile platform coordinate system, robot base coordinate system, robot end coordinate system, camera coordinate system, sleeve coordinate system, installation workpiece coordinate system, and determine the relative position relationship between the coordinate systems of each part; S3, performing hand-eye calibration and tightening end effector calibration; determining the relative position relationship between the camera (301) and the sleeve (302) through hand-eye calibration, obtaining the transformation matrix of the camera coordinate system relative to the robot end coordinate system, and obtaining the transformation matrix of the sleeve coordinate system relative to the robot end coordinate system through tightening end effector calibration; S4, teaching the photographing point and setting the photographing parameters; through manual teaching, ensure that the bolt to be tightened is located at the center of the field of view of the camera (401), and after ensuring that a clear and identifiable image of the bolt to be tightened without ghosting or blurring can be taken, record the position information and photographing parameters of the end of the collaborative robot (2) in the robot base coordinate system, and after obtaining the photographing point of a bolt to be tightened, calculate the photographing points of the remaining bolts to be tightened based on the product digital model information; setting the photographing parameters includes setting the exposure time and gain; S5, performing path planning and offline programming; planning the movement path of the collaborative robot (2) according to the photographing points of the bolts to be tightened, the product digital model information, and the relative positions of the entire tightening system and the system to be tightened obtained in step S4, to ensure the highest tightening efficiency, and using offline programming to ensure that the collaborative robot (2) can run in an offline state to reach each photographing point, thus completing the entire path planning and offline programming workflow; S6. Setting the process parameters of the tightening gun (301) according to the actual working conditions to meet the tightening requirements; S7, based on the different pre-tightening states of the bolts, each photographing point obtained in step S4 is corrected; the collaborative robot (2) first moves according to the path preset by the offline programming, and after reaching each photographing point, the laser displacement sensor (403) is used to ensure that the height from the camera (401) to the upper surface of each bolt cap remains unchanged, so as to realize the correction of each photographing point; S8, identifying the center position of the bolt to be tightened; after the end of the collaborative robot (2) reaches the corrected photographing point, the camera (401) is started to take a photo, and the image is transmitted to the integrated industrial computer. The obtained image is identified and processed using a preset algorithm program in the integrated industrial computer, and the precise position of the center of each bolt to be tightened in the robot base coordinate system is obtained by designing a multi-layer screening method; S9, the end of the collaborative robot (2) moves to the precise position obtained in step S8, runs the cap-finding program, controls the bolt cap to be inserted into the sleeve (302), the cylinder (303) pushes the reaction force arm (304) to extend, against the installation workpiece, the tightening gun (301) starts tightening, and the bolt rotates with the sleeve (302) until the tightening reaches the torque set by the processing task to complete the tightening; S10, after the bolt is tightened, the cylinder (303) works, the reaction force arm (304) retracts, and the sleeve (302) first rotates slightly in the opposite direction of tightening to create a gap between its inner cavity and the side surface of the bolt cap, and then the end moves in the vertical direction to separate the sleeve (302) and the bolt; S11. The integrated industrial computer makes a judgment. If there are still bolts to be tightened, steps S7-S10 are repeated until all tightening tasks are completed; if all tightening tasks have been completed, the system returns to the initial position.

5. The operating method of the seat ring gasket robot adaptive tightening system according to claim 4 is characterized in that: In step S7, the laser displacement sensor (403) is used to ensure that the height from the camera (401) to the upper surface of each bolt cap remains unchanged, and the correction of each photographing point is achieved specifically as follows: The preset height from the camera (401) to the upper surface of the bolt cap is set as h0, and the default height at which the end moves to each photographing point for photographing is H. The actual height h from the camera (401) to the upper surface of the bolt cap varies due to the different pre-tightening states of each bolt to be tightened. The value of the actual height h is measured by the laser displacement sensor (403), and correction is performed at each photographing point according to the difference between the actual height h and h0. The formula is expressed as follows: Wherein, H' represents the corrected height at which the end point moves to each photographing point for taking photos.

6. The operating method of the seat ring gasket robot adaptive tightening system according to claim 5, characterized in that: Step S8 specifically includes: S81. The bolt to be tightened is a hexagonal head, and its top view consists of a regular hexagon and an inscribed circle of the hexagon. First, the image obtained at the current shooting point is processed in the image coordinate system, and the inscribed circle is first identified through multi-layer screening to obtain the position data of the center of the circle; S82, delineating an ROI region with the center of the circle as the center, screening the six sides of the regular hexagon, and after screening the six sides, obtaining the six intersection points of the six sides as the six corner points of the regular hexagon; taking the average of the coordinates of the six points as the precise position of the center of the bolt to be tightened at the current photographing point in the image coordinate system, and then transforming the precise position of the center of the bolt to be tightened at the current photographing point in the robot base coordinate system through the positional relationship between the coordinate systems; S83, traverse each corrected photographing point, repeat steps S81-S82, and obtain the precise position of the center of each bolt to be tightened in the base coordinate system.

7. The operating method of the seat ring gasket robot adaptive tightening system according to claim 6, characterized in that: Step S81 specifically includes: S811. First, the fitting ellipses of all the bolts in the image are obtained, and the first-level screening is performed on the fitting ellipses based on their perimeter and area according to the following formula: Among them, S and C are the area and perimeter of the ellipse currently involved in the first-level screening and fitting, respectively. MIN , S MAX , C MIN , C MAX They respectively represent the minimum and maximum values ​​of the area of ​​the fitted ellipse and the minimum and maximum values ​​of the perimeter of the fitted ellipse that meet the set conditions; S812, perform the second level screening, select two fitting ellipses from the remaining fitting ellipses after the first level screening in turn to calculate the center distance between the two fitting ellipses, and only select and retain one of the two fitting ellipses whose center distance is too close; that is: First calculate the center distance L of the two fitting ellipses, the formula is expressed as: Among them, (x m ,y m ), (x n ,y n ) represents the coordinates of the centers of the two fitted ellipses involved in the calculation in the image coordinate system; Then compare it with the maximum value L0 of the center distance between the two fitted ellipses to decide whether to filter out one of the fitted ellipses. The formula is expressed as: The remaining fitted ellipses after the second level of screening meet the perimeter and area requirements, and there are no other fitted ellipse centers near their centers; S813, perform the third level screening, and perform roundness screening on the remaining fitted ellipses after the second level screening, and the formula is expressed as: Among them, a represents the semi-major axis length of the fitted ellipse, b represents the semi-minor axis length of the fitted ellipse, and R0 is the set roundness requirement; the fitted ellipse retained at last is used as the inscribed circle of the bolt; S814. After the above three levels of screening, the inscribed circles of all bolts in the image are screened out, and then the inscribed circle with the center closest to the center of the image is screened out as the inscribed circle of the bolt to be tightened at the current photographing point; specifically: First calculate the coordinates of the center of the image (x0, y0), the formula is: Where W represents the width of the image and H represents the height of the image; Then calculate the distance from the center of each inscribed circle to the center of the image, and find the shortest distance. The formula is: L Cmin =min{L Ci |i∈[1,2,...,n]}; Among them, L Ci represents the distance from the center of the i-th inscribed circle to the center of the image, L Cmin It represents the shortest distance from the center of the image. The center coordinates of the circle corresponding to this distance are the coordinates of the center of the inscribed circle of the bolt to be tightened at the current shooting point in the image coordinate system, recorded as (x c0 ,y c0 ).

8. The operating method of the seat ring gasket robot adaptive tightening system according to claim 7, characterized in that: Step S82 specifically includes: S821, taking the center of the inscribed circle of the bolt to be tightened at the current photographing point as the center and the entire hexagonal rectangular area including the projection of the bolt cap as the ROI area; and filtering out all line segments in the ROI area from the image, the formula is expressed as: Among them, W R and H R Indicates the width and height of the ROI area, (x A ,y A ) and (x B ,y B ) represent the two endpoints of the line segment respectively; S822, after all line segments in the ROI area are screened out, line segments that are judged to be repeated are screened out according to the cosine values ​​and midpoint distances between the line segments, and are divided into six groups; specifically: First calculate the cosine between the two line segments When the cosine value satisfies When , the two line segments are parallel, and the two line segments are considered to be repeated and classified into the same group; Among them, P represents the minimum cosine value for determining whether two straight lines are parallel, A and B represent the vectors corresponding to the two line segments; |A| and |B| are the moduli of the two vectors; Then, the midpoint distance is used to filter out the cases where the sides are parallel because they are opposite sides of the hexagon; the formula is expressed as: Among them, (x 1a ,y 1a )、(x 1b ,y 1b )、(x 1c ,y 1c ) represent the coordinates of the two endpoints and the midpoint of line segment 1, respectively. (x 2a ,y 2a )、(x 2b ,y 2b )、(x 2c ,y 2c ) represent the coordinates of the two endpoints and the midpoint of line segment 2 respectively, and line segment 1 and line segment 2 are judged to be parallel; L c0 Indicates the maximum value of the distance between the midpoints of the two line segments. When the distance between the midpoints of the two line segments does not exceed L c0 , then keep the judgment that these two line segments are repeated; After judging the cosine value and midpoint distance, six groups of line segments are obtained, and each line segment in the group is judged to be repeated; S823. According to the distance from the midpoint of the line segment to the center of the inscribed circle, select the line segment representing each side of the regular hexagon from each group. The formula is: Among them, l 1c , l 2c They represent the distances from the center of line segment 1 and line segment 2 in a group to the center of the inscribed circle respectively; each time the line segment with the longest distance to the center of the inscribed circle is retained, after all the line segments in the group are traversed, the last line segment retained represents one side of the regular hexagon. After all six groups are screened, six line segments representing the six sides of the regular hexagon are obtained; S824. According to the straight line equations of the six line segments obtained in step S823, the intersection points where the six straight lines intersect each other are obtained. The formula is: The general equation of the straight line on which each of the six line segments lies: A i x+B i y+C i =0(i=1,2,...,6); Intersection calculation formula: Among them, A i , B i , C i are the coefficients of the general equation of line i, A j , B j , C j are the coefficients of the general equation of line j, (x ij ,y ij ) is the intersection point of lines i and j Then, based on the fact that the distance from the intersection of non-adjacent straight lines to the center of the inscribed circle is greater than the distance from the intersection of adjacent straight lines to the center of the inscribed circle, non-adjacent straight line intersections are screened out. The formula is: Among them, L c1 is the set distance threshold, exceeding the distance threshold L c1 The intersection points are considered as non-adjacent straight line intersection points and are discarded; the six intersection points retained after final screening are the six corner points of the regular hexagon, and the six corner points are recorded as x n ,n=1,2,...,6; S825, calculate the coordinates (x c ,y c ): Convert the image coordinate system to the robot base coordinate system according to (x c ,y c ) calculates the precise position of the center of the bolt to be tightened at the current photographing point in the robot base coordinate system, and then guides the end of the collaborative robot (2) to move to the accurate position for tightening.

9. The operating method of the seat ring gasket robot adaptive tightening system according to claim 4, characterized in that: Step S9 specifically includes: S91. According to the precise position obtained in step S8, the end of the collaborative robot (2) first moves in the horizontal direction until the axis of the bolt is in line with the axis of the sleeve (302), and then the end is fed axially as a whole, and the sleeve (302) approaches the surface of the bolt. Different feeding and tightening methods are required according to the different pre-tightening states of each bolt to be tightened; the formula is expressed as: Wherein, h is the height of the camera (401) relative to the upper surface of the bolt cap obtained by the laser displacement sensor (403) before the photographing height adjustment, and h0 is the photographing height; S92, when h≥h0, the bolt has been pre-tightened in place and one-time feeding is adopted; specifically: First, the cap search is performed, and the end of the collaborative robot (2) is fed along the axial direction h0-h t +h l , where h t represents the axial distance difference between the lower surface of the sleeve (302) and the camera (401), h l Indicates the thickness of the bolt cap; After the feeding is completed, if the bolt is not inserted into the sleeve (302), but the lower surface of the sleeve (302) contacts the upper surface of the bolt, the feeding cannot continue. At this time, the spring is compressed by a force of h. l , the sleeve (302) is controlled by the tightening gun (301) to move at a lower angular velocity w l After slowly rotating one circle, when the inner cavity of the sleeve (302) and the shape of the bolt cap completely coincide with each other, the bolt cap is inserted into the sleeve (302) under the elastic force of the spring and rotates with the sleeve (302) to complete the cap search; After the cap is found, the reaction arm (304) is pushed out by the cylinder (303) to press against the edge of the workpiece, and the tightening gun (301) controls the sleeve (302) to move at a higher angular velocity w h Rotate to tighten the bolts; when the tightening torque reaches the task requirement, the tightening is completed; S93, when h<h0, the bolt is not pre-tightened in place, and the distance between the upper surface of the bolt and the installation workpiece is h0+h l -h, when tightening, the total axial feed amount of the end of the collaborative robot (2) increases by h0-h compared with the case of one-time feeding. In this case, multiple feeding is adopted, specifically: First, the end of the collaborative robot (2) still feeds h0-h along the axial direction t +h l , and performs the same cap-finding operation as the tightening process of one feed; after the cap-finding is completed, the lower surface of the sleeve (302) is h0-h away from the installation workpiece, and the end of the collaborative robot (2) is controlled to feed downward again h0-h, the bolt is inserted into the inner cavity of the sleeve (302), and the lower surface of the sleeve (302) fits with the installation workpiece; then, the cylinder (303) pushes the reaction force arm (304) to extend and press against the edge of the installation workpiece, and the tightening gun (301) controls the sleeve to move at a higher angular velocity w h Rotate to tighten the bolt, and when the tightening torque reaches the task requirement, the tightening is completed.

Images