CN112025677A - Automatic guiding glue supplementing system and method based on visual detection - Google Patents
Automatic guiding glue supplementing system and method based on visual detection Download PDFInfo
- Publication number
- CN112025677A CN112025677A CN202010739543.0A CN202010739543A CN112025677A CN 112025677 A CN112025677 A CN 112025677A CN 202010739543 A CN202010739543 A CN 202010739543A CN 112025677 A CN112025677 A CN 112025677A
- Authority
- CN
- China
- Prior art keywords
- glue
- industrial robot
- gluing
- detection
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/0075—Manipulators for painting or coating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05C—APPARATUS FOR APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05C5/00—Apparatus in which liquid or other fluent material is projected, poured or allowed to flow on to the surface of the work
- B05C5/02—Apparatus in which liquid or other fluent material is projected, poured or allowed to flow on to the surface of the work the liquid or other fluent material being discharged through an outlet orifice by pressure, e.g. from an outlet device in contact or almost in contact, with the work
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/04—Viewing devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/0081—Programme-controlled manipulators with master teach-in means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Manipulator (AREA)
Abstract
The invention relates to the technical field of gluing, in particular to an automatic guiding glue supplementing system based on visual detection, which comprises a robot, a glue gun, a three-mesh all-directional camera and an industrial control cabinet, wherein the glue gun is fixed on the industrial robot, and the three-mesh all-directional camera is fixed on the glue gun, the invention adopts the three-mesh all-directional camera to shoot a gluing picture to judge the continuity of gluing by designing, and automatically supplements glue to a glue breaking part according to a time period corresponding to the glue breaking section, thereby solving the problems that the prior enterprises generally adopt a machine visual detection method to detect the gluing quality, and once the glue breaking defect occurs, the production line is stopped and the alarm is given, and the repair is carried out in a manual intervention mode, so that the production beat is slowed down and the labor is consumed in the whole automobile manufacturing process, and compared with the prior gluing visual detection device, the scheme can not only, the glue section with quality problems can be repaired, so that the production efficiency is improved, and the labor is saved.
Description
Technical Field
The invention relates to the technical field of gluing, in particular to an automatic guiding glue supplementing system and method based on visual detection.
Background
The vehicle material is diversified and developed to high-strength steel, aluminum alloy, magnesium alloy, engineering plastics and composite materials on the basis of the traditional steel material, different from the traditional steel vehicle body, the white vehicle body is applied with a new material in a large area, the effective connection is difficult to realize by the conventional welding technology due to the differentiated physical properties among different materials, the bonding technology is the connection technology for connecting the materials together through the actions of chemical reaction or physical solidification and the like between an adhesive and a connected piece, the difficult problem of the connection of different materials is solved, the vehicle body strength is improved to a great extent, the application in the light weight process of the vehicle is more and more extensive, most of the bonding technology is realized through an industrial robot gluing mode, the special effects on the aspects of improving the comfort and the safety of the vehicle and prolonging the service life of the vehicle are realized, but because the adhesive is fluid, air bubbles are easily mixed in the middle of the adhesive, this defect can seriously affect the quality of the automobile. The existing enterprises generally adopt machine vision to detect the gluing quality, and once the gluing defect occurs, the production line is stopped and the alarm is given, and the glue is repaired in a manual intervention mode, so that the whole automobile manufacturing process slows down the production beat and consumes manpower.
In summary, the present invention solves the existing problems by designing an automatic guided glue filling system and method based on visual inspection.
Disclosure of Invention
The invention aims to provide an automatic guiding glue supplementing system and method based on visual detection, which are used for solving the problem that a production line needs to be stopped and manual glue supplementing is needed after a glue breaking phenomenon is found in the existing automobile manufacturing gluing process.
In order to achieve the purpose, the invention provides the following technical scheme:
the utility model provides an automatic guide is mended and is glued system based on visual detection, includes robot, glues rifle, three mesh all-round cameras and industrial control cabinet, it fixes at industrial robot to glue the rifle, three mesh all-round cameras are fixed on gluing the rifle.
Further, contain industrial computer, power module and heat dissipation module in the industrial control cabinet, industrial robot passes through the device net twine and links to each other with the industrial control cabinet in the industrial control cabinet, links to each other with the all-round camera of trinocular through the IO line, industrial robot includes protocol cables such as ProfiNet, ProfiBus, Ethernet with the communication mode of industrial computer, industrial robot is six industrial robot.
Furthermore, the three-eye all-directional camera has hard triggering and soft triggering functions, a hard triggering wiring terminal of the three-eye all-directional camera is connected with the industrial robot through an IO line, and the three-eye all-directional camera is an integrated light source.
Further, the method comprises a teaching stage and an operation stage.
Further, the teaching stage specifically comprises the following steps:
s1: teaching the gluing track of the industrial robot, fixing a workpiece at a tool position and keeping the workpiece still, manually teaching the gluing motion track, the gluing speed and the gluing amount of the industrial robot, storing the settings in an industrial robot controller, and then carrying out gluing operation by the industrial robot according to the settings;
s2: the method comprises the following steps that an industrial robot is used for gluing and controlling a three-eye all-directional camera to collect sample pictures, the industrial robot is used for gluing according to a teaching track, when the gluing is started, the industrial robot triggers the three-eye all-directional camera to take a picture through an I/O line, and triggers the three-eye all-directional camera to stop taking the picture when the gluing is finished, the image collected by the three-eye all-directional camera is transmitted to an industrial personal computer through network communication (TCP), the industrial robot and the industrial personal computer perform periodic data exchange through an industrial bus (DeviceNet) in the whole gluing process, the communication data comprise gluing state data, industrial robot terminal speed, industrial personal computer state data and the like, and the received relationship of the industrial robot terminal speed changing along with time is stored by the industrial;
s3: teaching pictures and parameters, receiving pictures shot by a camera at different positions by an industrial personal computer, and setting parameters frame by frame for detecting the quality of adhesive tapes at different positions:
selecting an optimal picture: at each shooting position, the three-eye all-directional camera can acquire three pictures, and a picture which is most easily identified by the adhesive tape needs to be selected as a picture to be detected.
Selecting an adhesive tape detection section: the adhesive tape in the picture to be detected needs to select one section as a detection section. The method comprises the following steps of sequentially selecting a starting point, a plurality of intermediate points and an end point near the central line of an adhesive tape as detection anchor points by using a point selection tool, wherein adjacent detection anchor points form a detection section, the plurality of detection sections form a detection section, and the detection section detects the edges of the two sides of the adhesive tape by default;
adjusting detection algorithm parameters: the adhesive tape pictures shot at different positions have different picture brightness, picture contrast, adhesive tape quality tolerance and the like, so detection algorithm parameters need to be adjusted, and the detection parameters comprise filtering method selection, a filtering coefficient, an edge search range value, a position degree error value, an adhesive tape width error value, background color and the like;
in addition to the parameters set frame by frame, the pixel position of the glue gun head in the picture needs to be selected and the physical size corresponding to a single pixel of the image needs to be measured;
s4: and storing the data, storing the teaching pictures into a local folder, and storing the teaching parameters and the terminal speed of the continuous motion of the industrial robot into a database.
Further, the specific steps of the operation stage are as follows:
s5: the industrial robot is used for gluing and controlling the camera to take a picture, similarly to the teaching stage, the industrial robot is used for gluing according to a teaching track and controlling the camera to pick a picture, and the upper computer system is used for exchanging data with the industrial robot and receiving an image transmitted by the trinocular camera;
s6: detecting the glue breaking condition of the pictures, and carrying out glue breaking detection on the collected pictures one by one according to teaching parameters;
s7: repeatedly detecting all the pictures, and if all the pictures are not broken, finishing gluing the current workpiece;
s8: and if the glue is broken in the picture, entering a glue supplementing mode.
Further, the step of detecting the broken glue at S6 is as follows:
s61: interpolating the taught detection anchor points to obtain more detection anchor points, and forming detection sections between adjacent anchor points;
s62: for a detection segment, a rectangular detection area is intercepted, and fuzzy filtering and gradient statistics are carried out in the rectangle along the width direction; if the gradient value at a certain position exceeds a threshold value, the position is considered as an edge position, otherwise, the segmentation cannot position the edge;
s63: repeating the above steps to locate the edges of all the detected segments. If any detection segment can not locate the edge, the picture is considered to have the glue failure condition at the segment, and a pair of anchor points of the segment is recorded. And if the adjacent subsections have broken glue, combining the two subsections into a broken glue subsection.
Further, the glue filling mode in S8 is specifically as follows:
s81: determining the starting time and the end time of the glue breaking section according to a glue supplementing algorithm;
s82: the industrial robot moves to supplement the glue, the industrial robot moves again according to the glue-supplementing track and controls the camera to pick the picture, the glue-supplementing head is closed by default at the time, when the glue-supplementing starting time t1 is reached, the upper computer sends a glue-supplementing head opening command, and the industrial robot starts to supplement the glue; when the glue filling termination time t2 is reached, the upper computer sends a glue head closing command, the industrial robot stops gluing, and the command can be sent in advance by a certain amount of time due to the time delay of communication;
s83, rechecking the picture, detecting the picture of the glue supplement again, if the glue is not broken, finishing the gluing of the current workpiece; if the glue is still broken, the other accidents are indicated, and an alarm is given.
Further, the specific manner of determining the starting time and the ending time of the interrupted rubber segment in S81 is as follows:
s811: calculating the pixel distance between the glue breaking segment and the glue gun head, wherein the position of the broken glue in the glue breaking picture is the glue breaking segment as described by a detection algorithm, the glue breaking segment is described by a pair of detection anchor points which are respectively a starting anchor point and an ending anchor point, and the pixel distance between the starting anchor point and the glue gun head and the pixel distance between the ending anchor point and the glue gun head are respectively calculated along a gluing path;
s812: the pixel distance is converted into a physical distance, the physical size corresponding to a single pixel is measured, and the physical distance s1 between the initial anchor point and the glue gun head and the physical distance s2 between the termination anchor point and the glue gun head can be calculated by multiplying the parameter by the pixel distance;
s813: and calculating the glue breaking time through a V-T diagram of the industrial robot. The relation of the tail end speed of the industrial robot, which is acquired in the teaching stage, changing along with time forms a V-T diagram, and the shooting time of the current glue breaking image is known to be T0, the starting time of glue breaking is assumed to be T1, the total glue spreading distance of the industrial robot between T1 and T0 is s1, and the glue spreading speed of the industrial robot between T1 and T0 can be found out in the V-T diagram, so that the starting time T1 of glue breaking can be found out, and the end time T2 can be found out in the same way.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, the glue coating continuity is judged by shooting a glue coating picture through a three-mesh omnibearing camera through design, and the glue-broken part is automatically repaired according to the time period corresponding to the glue-broken section, so that the problems that the production beat is slowed down and the labor is consumed in the whole automobile manufacturing process and the whole automobile is produced due to the fact that the existing enterprises generally adopt a machine vision detection method to detect the glue coating quality, once the glue-broken defect occurs, the production line is stopped and the alarm is given, and the repair is carried out through a manual intervention mode are solved.
Drawings
FIG. 1 is a schematic structural diagram of an automatic glue filling system based on visual inspection according to the present invention;
FIG. 2 is a communication diagram of an automatic glue filling system based on visual inspection according to the present invention;
FIG. 3 is a flow chart of a teaching phase of an automatic glue filling method based on visual inspection according to the present invention;
FIG. 4 is a flow chart of an operation phase of an automatic glue filling method based on visual inspection according to the present invention;
fig. 5 is a flow chart of a glue filling algorithm of the automatic glue filling method based on visual inspection.
In the figure: 1-industrial robot, 2-glue gun, 3-three-mesh omnibearing camera and 4-industrial control cabinet.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.
Referring to fig. 1-5, the present invention provides a technical solution:
the utility model provides an automatic guide system of mending glue based on visual detection, includes robot 1, glues rifle 2, the all-round camera of three meshes 3 and industrial control cabinet 4, glues rifle 2 and fixes at industrial robot 1, and the all-round camera of three meshes 3 is fixed on gluing rifle 2.
The working process is as follows: when an industrial robot 1 starts to carry a glue gun 2 to glue a workpiece in a fixed track, the three-eye all-directional camera 3 is triggered to shoot through an IO line at the same time, after the three-eye all-directional camera 3 receives a shooting instruction of the industrial robot 1, the three-eye all-directional camera starts to shoot a gluing condition picture at a fixed frame rate and transmits the picture to an industrial control machine in an industrial control cabinet 4, a visual detection system in the industrial control machine detects the continuity of a glue strip in real time, if the visual detection system detects that the glue strip is broken, the system calculates a time period corresponding to a glue breaking section, after the gluing of the workpiece is finished, the system sends the time period corresponding to the glue breaking section to the industrial robot 1, and the industrial robot 1 starts to glue supplement again according to the preset track motion to the time period corresponding.
The specific embodiment is as follows:
as shown in fig. 1, an automatic glue filling system based on visual inspection includes: the system comprises an industrial robot 1, a three-eye all-directional camera 3, a glue gun 2 and an industrial control cabinet 4, wherein the industrial control cabinet 4 comprises an industrial control computer, a power supply module and a heat dissipation module;
the three-eye omnibearing camera 3 is fixed on the glue gun 2, the glue gun 2 is fixed on the industrial robot 1, wherein the three-eye omnibearing camera 3 integrates a light source, can image the whole angle around the glue gun 2, and avoids the condition that the glue gun 2 shields the adhesive tape in the single-camera view;
as shown in fig. 2, the industrial robot 1 is connected with an industrial personal computer in the industrial control cabinet 4 through a DeviceNet network cable and is connected with a hard trigger wiring terminal of the three-eye omnidirectional camera 3 through an IO cable;
an automatic guiding glue supplementing method based on visual detection comprises two stages of teaching and operation;
as shown in fig. 4, the teaching phase includes the following steps:
step 1: teaching an industrial robot 1 gluing track, fixing a workpiece at a tool position and keeping the workpiece still, manually teaching the industrial robot 1 gluing motion track, motion speed and gluing amount, storing the settings in a controller of the industrial robot 1, and then carrying out gluing operation by the industrial robot 1 according to the settings;
step 2: the industrial robot 1 gelatinizes and controls the three-eye all-directional camera 3 to collect sample pictures, the industrial robot 1 gelatinizes according to teaching tracks, when the gelatinizing is started, the industrial robot 1 triggers the three-eye all-directional camera 3 to take pictures through an I/O line, and triggers the three-eye all-directional camera 3 to stop taking pictures when the gelatinizing is finished, images collected by the three-eye all-directional camera 3 are transmitted to an industrial personal computer through network communication (TCP), in the whole gelatinizing process, the industrial robot 1 carries out periodic data exchange with the industrial personal computer through an industrial bus (DeviceNet), communication data comprise gelatinizing state data, the terminal speed of the industrial robot 1, the state data of the industrial personal computer and the like, and the received terminal speed of the industrial robot 1 is stored along with the time change relationship when the industrial personal computer is used.
And step 3: teaching pictures and parameters, receiving pictures shot by a camera at different positions by an industrial personal computer, and setting parameters frame by frame for detecting the quality of adhesive tapes at different positions:
selecting an optimal picture: at each shooting position, the three-eye omnidirectional camera 3 acquires three pictures, and a picture which is most easily identified by an adhesive tape is selected as a picture to be detected;
selecting an adhesive tape detection section: the method comprises the steps that an adhesive tape in a picture to be detected needs to select one section as a detection section, a point selection tool is utilized, a starting point, a plurality of intermediate points and an end point are sequentially selected near the central line of the adhesive tape as detection anchor points, adjacent detection anchor points form a detection section, the plurality of detection sections form the detection section, the detection section detects the edges of the two sides of the adhesive tape in a default mode, but the detection section can be set to be single-side edge detection or non-detection because the background of a workpiece where the adhesive tape is located is possibly complex;
adjusting detection algorithm parameters: the adhesive tape pictures shot at different positions have different picture brightness, picture contrast, adhesive tape quality tolerance and the like, so detection algorithm parameters need to be adjusted, and the detection parameters comprise filtering method selection, a filtering coefficient, an edge search range value, a position degree error value, an adhesive tape width error value, background color and the like;
in addition to the parameters set frame by frame, the pixel position of the head of the glue gun 2 in the picture needs to be selected and the physical size corresponding to a single pixel of the image needs to be measured;
and 4, step 4: storing data, storing the teaching pictures in a local folder, and storing the teaching parameters and the terminal speed of the continuous motion of the industrial robot 1 in a database;
as shown in fig. 5, the operation phase includes the following steps:
and 5: the industrial robot 1 coats glue and controls a camera to shoot, similarly to the teaching stage, the industrial robot 1 coats glue according to a teaching track and controls the camera to collect images, and an upper computer system keeps data exchange with the industrial robot 1 and receives images transmitted by the trinocular camera;
step 6: detecting the glue breaking condition of the pictures, and carrying out glue breaking detection on the collected pictures one by one according to teaching parameters;
and 7: repeatedly detecting all the pictures, and if all the pictures are not broken, finishing gluing the current workpiece;
and 8: if the glue is broken in the picture, entering a glue supplementing mode;
further, the glue breaking detection specifically comprises the following steps:
step 61: interpolating the taught detection anchor points to obtain more detection anchor points, and forming detection sections between adjacent anchor points;
step 62: for a detection segment, a rectangular detection area is truncated. In the rectangle, fuzzy filtering and gradient statistics are carried out along the width direction, if a gradient value at a certain position exceeds a threshold value, the position is considered as an edge position, otherwise, the edge cannot be positioned by the segment;
and step 63: repeating the steps to position the edges of all the detection segments, if any detection segment can not position the edge, determining that the glue failure condition exists in the segment of the picture, simultaneously recording a pair of anchor points of the segment, and if the glue failure exists in the adjacent segments, combining the two segments into a glue failure segment;
the glue filling mode specifically comprises the following steps:
step 81: determining the starting time and the end time of the glue breaking section according to a glue supplementing algorithm;
step 82: the industrial robot 1 moves to supplement the glue, the industrial robot 1 moves according to the gluing track again and controls the camera to pick up the picture, the gluing head is closed by default at this time, when the glue supplementing starting time t1 is reached, the upper computer sends a glue head opening command, the industrial robot 1 starts to glue, when the glue supplementing ending time t2 is reached, the upper computer sends a glue head closing command, the industrial robot 1 stops gluing, and due to the fact that time delay exists in communication, the command can be sent in advance for a certain amount of time;
and 83, rechecking the picture, detecting the picture of glue supplement again, and finishing gluing the current workpiece if the glue is not broken. If the glue is broken, indicating that other accidents occur, and giving an alarm for prompting;
further, the starting time and the ending time of the interrupted rubber section are determined in the following specific mode:
step 811: calculating the pixel distance between the glue breaking segment and the glue gun 2 head, wherein the position of glue breaking in the glue breaking picture is the glue breaking segment as described by a detection algorithm, the glue breaking segment is described by a pair of detection anchor points which are respectively a starting anchor point and an ending anchor point, and the pixel distance between the starting anchor point and the ending anchor point and the glue gun 2 head is respectively calculated along a glue coating path;
step 812: the pixel distance is converted into a physical distance, the physical size corresponding to a single pixel is measured, and the physical distance s1 between the initial anchor point and the glue gun 2 head and the physical distance s2 between the termination anchor point and the glue gun 2 head can be calculated by multiplying the parameter by the pixel distance;
step 813: according to the method, glue breaking time is calculated through an industrial robot 1V-T diagram, a V-T diagram is formed by the relation, collected in a teaching stage, of the tail end speed of the industrial robot 1 changing along with time, the shooting time of the current glue breaking image is known to be T0, the starting time of glue breaking is assumed to be T1, the total glue spreading distance of the industrial robot 1 between T1 and T0 is s1, the glue spreading speed of the industrial robot 1 between T1 and T0 can be found out in the V-T diagram, therefore, the starting time T1 of glue breaking can be found out, and the end time T2 can be found out in the same way.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. The utility model provides an automatic guide system of mending glue based on visual detection, includes robot (1), glues rifle (2), three mesh all-round camera (3) and industrial control cabinet (4), its characterized in that: glue rifle (2) and fix at industrial robot (1), three mesh all-round cameras (3) are fixed on gluing rifle (2).
2. The automatic guiding glue supplementing system based on the visual inspection is characterized in that: the industrial control cabinet (4) comprises an industrial personal computer, a power module and a heat dissipation module, the industrial robot (1) is connected with the industrial personal computer in the industrial control cabinet (4) through a DeviceNet network cable and is connected with the trinocular omni-directional camera (3) through an IO (input output) cable, the communication modes of the industrial robot (1) and the industrial personal computer comprise protocol cables such as ProfiNet, ProfiBus and Ethernet, and the industrial robot (1) is a six-axis industrial robot.
3. The automatic guiding glue supplementing system based on the visual inspection is characterized in that: the three-eye all-directional camera (3) has hard triggering and soft triggering functions, a hard triggering wiring terminal of the three-eye all-directional camera (3) is connected with the industrial robot (1) through an IO line, and the three-eye all-directional camera (3) is an integrated light source.
4. An automatic guiding glue supplementing method based on visual detection is characterized by comprising a teaching stage and an operation stage.
5. The visual inspection-based automatic guided glue filling method according to claim 4, wherein the teaching stage comprises the following steps:
s1: teaching an industrial robot (1) to glue a track, fixing a workpiece at a tool position and keeping the workpiece still, manually teaching the motion track, the motion speed and the gluing amount of gluing of the industrial robot (1), storing the settings in a controller of the industrial robot (1), and then carrying out gluing operation by the industrial robot (1) according to the settings;
s2: the industrial robot (1) coats the glue and controls the three-eye omnibearing camera (3) to collect a sample picture, the industrial robot (1) coats the glue according to a teaching track, when the gluing is started, the industrial robot (1) triggers the three-eye omnibearing camera (3) to take a picture through the I/O line, and triggers the three-eye omnibearing camera (3) to stop taking photos when the gluing is finished, the images collected by the three-eye omnibearing camera (3) are transmitted to an industrial personal computer through network communication (TCP), in the whole gluing process, the industrial robot (1) carries out periodic data exchange with an industrial personal computer through an industrial bus (DeviceNet), communication data comprise gluing state data, the tail end speed of the industrial robot (1), the state data of the industrial personal computer and the like, and the industrial personal computer stores the received relation of the tail end speed of the industrial robot (1) changing along with time for subsequent glue filling algorithm;
s3: teaching pictures and parameters, receiving pictures shot by a camera at different positions by an industrial personal computer, and setting parameters frame by frame for detecting the quality of adhesive tapes at different positions:
selecting an optimal picture: at each shooting position, the three-eye all-directional camera (3) can acquire three pictures, and one picture which is most easily identified by the adhesive tape needs to be selected as a picture to be detected.
Selecting an adhesive tape detection section: the adhesive tape in the picture to be detected needs to select one section as a detection section. The method comprises the following steps of sequentially selecting a starting point, a plurality of intermediate points and an end point near the central line of an adhesive tape as detection anchor points by using a point selection tool, wherein adjacent detection anchor points form a detection section, the plurality of detection sections form a detection section, and the detection section detects the edges of the two sides of the adhesive tape by default;
adjusting detection algorithm parameters: the adhesive tape pictures shot at different positions have different picture brightness, picture contrast, adhesive tape quality tolerance and the like, so detection algorithm parameters need to be adjusted, and the detection parameters comprise filtering method selection, a filtering coefficient, an edge search range value, a position degree error value, an adhesive tape width error value, background color and the like;
in addition to the parameters set frame by frame, the pixel position of the head of the glue gun (2) in the picture needs to be selected and the physical size corresponding to a single pixel of the image needs to be measured;
s4: and storing data, storing the teaching pictures in a local folder, and storing the teaching parameters and the terminal speed of the continuous motion of the industrial robot (1) in a database.
6. The visual inspection-based automatic guided glue replenishing method according to claim 4, wherein the operation stage comprises the following specific steps:
s5: the industrial robot (1) is used for gluing and controlling the camera to take a picture, similarly to the teaching stage, the industrial robot (1) is used for gluing according to a teaching track and controlling the camera to pick a picture, and the upper computer system keeps data exchange with the industrial robot (1) and receives an image transmitted by the three-eye camera;
s6: detecting the glue breaking condition of the pictures, and carrying out glue breaking detection on the collected pictures one by one according to teaching parameters;
s7: repeatedly detecting all the pictures, and if all the pictures are not broken, finishing gluing the current workpiece;
s8: and if the glue is broken in the picture, entering a glue supplementing mode.
7. The visual inspection-based automatic guided glue filling method as claimed in claim 6, wherein the step of interrupting the glue inspection at S6 comprises the following steps:
s61: interpolating the taught detection anchor points to obtain more detection anchor points, and forming detection sections between adjacent anchor points;
s62: for a detection segment, a rectangular detection area is intercepted, and fuzzy filtering and gradient statistics are carried out in the rectangle along the width direction; if the gradient value at a certain position exceeds a threshold value, the position is considered as an edge position, otherwise, the segmentation cannot position the edge;
s63: repeating the above steps to locate the edges of all the detected segments. If any detection segment can not locate the edge, the picture is considered to have the glue failure condition at the segment, and a pair of anchor points of the segment is recorded. And if the adjacent subsections have broken glue, combining the two subsections into a broken glue subsection.
8. The visual inspection-based automatic guided glue filling method as claimed in claim 6, wherein the glue filling mode in S8 is as follows:
s81: determining the starting time and the end time of the glue breaking section according to a glue supplementing algorithm;
s82: the glue supplementing is carried out by the industrial robot (1), the industrial robot (1) moves according to the glue supplementing track again and controls the camera to pick up the picture, the glue head is closed by default at the time, when the glue supplementing starting time t1 is reached, the upper computer sends a glue head opening command, and the industrial robot (1) starts to conduct glue supplementing; when the glue filling termination time t2 is reached, the upper computer sends a glue head closing command, the industrial robot (1) stops gluing, and the command can be sent in advance by a certain amount of time due to the time delay of communication;
s83, rechecking the picture, detecting the picture of the glue supplement again, if the glue is not broken, finishing the gluing of the current workpiece; if the glue is still broken, the other accidents are indicated, and an alarm is given.
9. An automatic adhesive-filling guiding method based on visual inspection as claimed in claim 8, wherein said S81 determines the starting time and the ending time of the interrupted adhesive segment by:
s811: calculating the pixel distance between the glue breaking segment and the head of the glue gun (2), wherein the position of the broken glue in the glue breaking picture is the glue breaking segment as described by a detection algorithm, the glue breaking segment is described by a pair of detection anchor points which are respectively a starting anchor point and an ending anchor point, and the pixel distance between the starting anchor point and the ending anchor point and the head of the glue gun (2) is calculated along a glue coating path;
s812: the pixel distance is converted into a physical distance, the physical size corresponding to a single pixel is measured, and the physical distance s1 between the initial anchor point and the head of the glue gun (2) and the physical distance s2 between the final anchor point and the head of the glue gun (2) can be calculated by multiplying the parameter by the pixel distance;
s813: and calculating the glue breaking time through a V-T diagram of the industrial robot (1). The relation that the tail end speed of the industrial robot (1) collected in the teaching stage changes along with time forms a V-T diagram, the shooting time of the current glue breaking image is known to be T0, the starting time of glue breaking is assumed to be T1, the total distance of glue coating of the industrial robot (1) between T1 and T0 is assumed to be s1, and the glue coating speed of the industrial robot (1) between T1 and T0 can be found out in the V-T diagram, so that the starting time T1 of glue breaking can be found out, and the end time T2 can be found out in the same way.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010739543.0A CN112025677B (en) | 2020-07-28 | 2020-07-28 | Automatic guiding glue supplementing system and method based on visual detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010739543.0A CN112025677B (en) | 2020-07-28 | 2020-07-28 | Automatic guiding glue supplementing system and method based on visual detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112025677A true CN112025677A (en) | 2020-12-04 |
| CN112025677B CN112025677B (en) | 2023-09-26 |
Family
ID=73583385
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010739543.0A Active CN112025677B (en) | 2020-07-28 | 2020-07-28 | Automatic guiding glue supplementing system and method based on visual detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112025677B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112894807A (en) * | 2021-01-13 | 2021-06-04 | 深圳市玄羽科技有限公司 | Industrial automation control device and method |
| CN113546811A (en) * | 2021-08-10 | 2021-10-26 | 一汽解放汽车有限公司 | Gluing monitoring equipment and gluing quality monitoring method |
| CN113941483A (en) * | 2021-11-26 | 2022-01-18 | 深圳了然视觉科技有限公司 | Glue coating quality detection and automatic glue supplementing system based on vision |
| CN114324395A (en) * | 2021-12-30 | 2022-04-12 | 广州市斯睿特智能科技有限公司 | Following type 3D gluing visual detection device and detection method |
| CN114733722A (en) * | 2022-06-14 | 2022-07-12 | 江苏舜奇机电科技有限公司 | Defective product detection module in intelligent glue coating assembly system for rail transit vehicle glass |
| CN115228690A (en) * | 2022-08-08 | 2022-10-25 | 深圳市深赛尔股份有限公司 | Paint surface repairing device and method based on environment-friendly water-based coil steel coating |
| CN116532328A (en) * | 2023-04-21 | 2023-08-04 | 浙江金麦特自动化系统有限公司 | PCB gluing method |
| CN116777888A (en) * | 2023-06-30 | 2023-09-19 | 广州高迪机电工程有限公司 | Self-adaptive compensation correction method for adhesive width by visual detection system during angular adhesive coating |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11106U (en) * | 1998-11-13 | 1999-08-17 | 極東産機株式会社 | Automatic gluing machine |
| US20070000442A1 (en) * | 2000-09-29 | 2007-01-04 | Josef Schucker | Device for applying adhesive to a workpiece |
| CN1921954A (en) * | 2003-12-23 | 2007-02-28 | 奎斯有限公司 | Method for automatically applying and controlling a structure applicable on a substrate and device for carrying out said method |
| CN106881242A (en) * | 2017-04-12 | 2017-06-23 | 广州瑞松北斗汽车装备有限公司 | Vision follows detection coating system |
| CN207133539U (en) * | 2017-07-31 | 2018-03-23 | 昆山龙腾光电有限公司 | A kind of frame gum coating equipment |
| CN108031614A (en) * | 2017-12-14 | 2018-05-15 | 四川福德机器人股份有限公司 | A kind of gluing automatic compensating method of gas meter, flow meter and the device using this method |
| CN109972827A (en) * | 2019-05-09 | 2019-07-05 | 广东博智林机器人有限公司 | Spray robot and control method and control device, computer readable storage medium |
| CN110355759A (en) * | 2019-07-05 | 2019-10-22 | 保定科海自动化科技有限公司 | A kind of industrial robot gluing control system of view-based access control model |
| WO2020037641A1 (en) * | 2018-08-24 | 2020-02-27 | 深圳配天智能技术研究院有限公司 | Glue applying robot and glue applying method |
| CN210279674U (en) * | 2019-02-22 | 2020-04-10 | 吉林省吉邦自动化科技有限公司 | Prevent marginal leakage but continuity rubber coating rotation type rubber coating equipment |
| CN111192237A (en) * | 2019-12-16 | 2020-05-22 | 重庆大学 | Glue coating detection system and method based on deep learning |
-
2020
- 2020-07-28 CN CN202010739543.0A patent/CN112025677B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11106U (en) * | 1998-11-13 | 1999-08-17 | 極東産機株式会社 | Automatic gluing machine |
| US20070000442A1 (en) * | 2000-09-29 | 2007-01-04 | Josef Schucker | Device for applying adhesive to a workpiece |
| CN1921954A (en) * | 2003-12-23 | 2007-02-28 | 奎斯有限公司 | Method for automatically applying and controlling a structure applicable on a substrate and device for carrying out said method |
| CN106881242A (en) * | 2017-04-12 | 2017-06-23 | 广州瑞松北斗汽车装备有限公司 | Vision follows detection coating system |
| CN207133539U (en) * | 2017-07-31 | 2018-03-23 | 昆山龙腾光电有限公司 | A kind of frame gum coating equipment |
| CN108031614A (en) * | 2017-12-14 | 2018-05-15 | 四川福德机器人股份有限公司 | A kind of gluing automatic compensating method of gas meter, flow meter and the device using this method |
| WO2020037641A1 (en) * | 2018-08-24 | 2020-02-27 | 深圳配天智能技术研究院有限公司 | Glue applying robot and glue applying method |
| CN210279674U (en) * | 2019-02-22 | 2020-04-10 | 吉林省吉邦自动化科技有限公司 | Prevent marginal leakage but continuity rubber coating rotation type rubber coating equipment |
| CN109972827A (en) * | 2019-05-09 | 2019-07-05 | 广东博智林机器人有限公司 | Spray robot and control method and control device, computer readable storage medium |
| CN110355759A (en) * | 2019-07-05 | 2019-10-22 | 保定科海自动化科技有限公司 | A kind of industrial robot gluing control system of view-based access control model |
| CN111192237A (en) * | 2019-12-16 | 2020-05-22 | 重庆大学 | Glue coating detection system and method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 张海波;: "煤矿胶带裂纹检测方案研究", 煤, no. 02, pages 9 - 10 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112894807A (en) * | 2021-01-13 | 2021-06-04 | 深圳市玄羽科技有限公司 | Industrial automation control device and method |
| CN113546811A (en) * | 2021-08-10 | 2021-10-26 | 一汽解放汽车有限公司 | Gluing monitoring equipment and gluing quality monitoring method |
| CN113941483A (en) * | 2021-11-26 | 2022-01-18 | 深圳了然视觉科技有限公司 | Glue coating quality detection and automatic glue supplementing system based on vision |
| CN114324395B (en) * | 2021-12-30 | 2024-01-19 | 广州市斯睿特智能科技有限公司 | Following type 3D gluing visual detection device and detection method |
| CN114324395A (en) * | 2021-12-30 | 2022-04-12 | 广州市斯睿特智能科技有限公司 | Following type 3D gluing visual detection device and detection method |
| CN114733722A (en) * | 2022-06-14 | 2022-07-12 | 江苏舜奇机电科技有限公司 | Defective product detection module in intelligent glue coating assembly system for rail transit vehicle glass |
| CN114733722B (en) * | 2022-06-14 | 2022-09-09 | 江苏舜奇机电科技有限公司 | Defective product detection module in intelligent glue coating assembly system for rail transit vehicle glass |
| CN115228690A (en) * | 2022-08-08 | 2022-10-25 | 深圳市深赛尔股份有限公司 | Paint surface repairing device and method based on environment-friendly water-based coil steel coating |
| CN115228690B (en) * | 2022-08-08 | 2023-08-08 | 深圳市深赛尔股份有限公司 | Paint surface repairing device and method based on environment-friendly water-based coil steel coating |
| CN116532328A (en) * | 2023-04-21 | 2023-08-04 | 浙江金麦特自动化系统有限公司 | PCB gluing method |
| CN116532328B (en) * | 2023-04-21 | 2024-03-29 | 浙江金麦特自动化系统有限公司 | PCB gluing method |
| CN116777888A (en) * | 2023-06-30 | 2023-09-19 | 广州高迪机电工程有限公司 | Self-adaptive compensation correction method for adhesive width by visual detection system during angular adhesive coating |
| CN116777888B (en) * | 2023-06-30 | 2024-02-06 | 广州高迪机电工程有限公司 | Self-adaptive compensation correction method for adhesive width by visual detection system during angular adhesive coating |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112025677B (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112025677A (en) | Automatic guiding glue supplementing system and method based on visual detection | |
| CN102430841A (en) | Arc welding robot laser vision seam tracking control method based on offline planning | |
| CN203791807U (en) | Welding robot | |
| CN105171742A (en) | 3D printing welding method using multi-degree-of-freedom robot | |
| JP2024503141A (en) | AGV scheduling method based on time estimation model | |
| CN103018881A (en) | Automatic focusing method and automatic focusing system based on infrared images | |
| CN102126068A (en) | Passive visual sensor based on weld automatic tracking of welding robot | |
| CN111689168A (en) | Remote control type belt self-moving tail control system | |
| CN106238871A (en) | A kind of intelligence gantry welding connection device | |
| CN105414821A (en) | Automatic tracking system for welding robot welding seam | |
| CN114434456A (en) | Machine room inspection robot and inspection method thereof | |
| CN105862080A (en) | Intelligent crust breaking system and method for aluminum reduction cells | |
| CN112882435A (en) | Data acquisition and image processing control system and method suitable for narrow space | |
| CN106271369A (en) | Railway frog intelligence welding robot | |
| CN111069740B (en) | Flexible control method and system for robot welding process | |
| CN109514439A (en) | A kind of control system for climbing wall type ship derusting by sandblasting equipment | |
| CN206366785U (en) | Railway frog intelligence welding robot | |
| CN109128439A (en) | CAD diagram paper technology guided robot automatic soldering method | |
| CN105022341A (en) | Device and method for controlling optical fiber flexible plate automatic fiber arrangement device | |
| CN205271133U (en) | High -frequency soldering intelligence control system | |
| CN114167830A (en) | Welding process monitoring and quality diagnosis method based on machine vision and edge intelligence | |
| CN115106621A (en) | All-position robot deep melting K-TIG welding system and control method | |
| CN207850285U (en) | A kind of auto parts machinery gluing quality dynamic on-line monitoring device | |
| CN204913101U (en) | Radiator automatic weld machine | |
| CN112975030A (en) | Control system of laser welding equipment and laser welding equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |