CN114056920B - Lamination machine based on machine vision and sheet calibration method and control method thereof - Google Patents
Lamination machine based on machine vision and sheet calibration method and control method thereof Download PDFInfo
- Publication number
- CN114056920B CN114056920B CN202111166209.1A CN202111166209A CN114056920B CN 114056920 B CN114056920 B CN 114056920B CN 202111166209 A CN202111166209 A CN 202111166209A CN 114056920 B CN114056920 B CN 114056920B
- Authority
- CN
- China
- Prior art keywords
- sheet
- area
- lifting
- material taking
- image
- 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.)
- Active
Links
- 238000003475 lamination Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 58
- 239000000463 material Substances 0.000 claims abstract description 254
- 238000007599 discharging Methods 0.000 claims abstract description 10
- 230000009466 transformation Effects 0.000 claims abstract description 10
- 230000007246 mechanism Effects 0.000 claims description 128
- 230000008569 process Effects 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 13
- 230000000903 blocking effect Effects 0.000 claims description 9
- 238000003708 edge detection Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 230000000630 rising effect Effects 0.000 abstract description 3
- 230000003028 elevating effect Effects 0.000 description 10
- 240000004282 Grewia occidentalis Species 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 6
- 230000001681 protective effect Effects 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000001629 suppression Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 239000011521 glass Substances 0.000 description 3
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 229910052744 lithium Inorganic materials 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 239000011347 resin Substances 0.000 description 2
- 229920005989 resin Polymers 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000007598 dipping method Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000003365 glass fiber Substances 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001050 lubricating effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
- B65G47/74—Feeding, transfer, or discharging devices of particular kinds or types
- B65G47/90—Devices for picking-up and depositing articles or materials
- B65G47/905—Control arrangements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G57/00—Stacking of articles
- B65G57/02—Stacking of articles by adding to the top of the stack
- B65G57/03—Stacking of articles by adding to the top of the stack from above
- B65G57/035—Stacking of articles by adding to the top of the stack from above with a stepwise downward movement of the stack
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G59/00—De-stacking of articles
- B65G59/02—De-stacking from the top of the stack
- B65G59/026—De-stacking from the top of the stack with a stepwise upward movement of the stack
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G61/00—Use of pick-up or transfer devices or of manipulators for stacking or de-stacking articles not otherwise provided for
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
- Y02P70/50—Manufacturing or production processes characterised by the final manufactured product
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
- Sheets, Magazines, And Separation Thereof (AREA)
Abstract
The utility model discloses a lamination machine based on machine vision, and a sheet calibration method and a control method thereof, wherein the lamination machine provided by the utility model introduces a sheet calibration method of the lamination machine based on machine vision, and combines a Yolo3 network and Hough transformation to realize stacking calibration of sheets, so that the typesetting of the sheets is more neat and the stacking stability is higher; on the other hand, the lamination machine provided by the utility model can further realize the automatic rising of the sheet lifting area and the automatic falling of the finished product lifting platform, so that the material taking height on the sheet lifting area is consistent with the material discharging height on the finished product lifting area, the mechanical manual operation is consistent, the typesetting efficiency of lamination is greatly improved, and the lamination machine can be directly applied to prepreg stacking, and the series of problems existing in the conventional manual prepreg stacking in the PCB production process are solved.
Description
Technical Field
The utility model belongs to the technical field of lamination machines, and particularly relates to a lamination machine based on machine vision, and a sheet calibration method and a control method thereof.
Background
The prepreg is one of the main materials necessary in the design process of the PCB, and is a sheet material prepared by dipping treated glass fiber cloth with resin glue solution and then performing heat treatment (pre-baking) to make the resin enter the B stage. In a PCB production workshop, different types of prepregs are stacked orderly according to a formula, and the prepregs are stacked manually at present, so that the PCB production workshop has the advantages of large workload, irregular stacking, low working efficiency, difficulty in synchronizing with a machine, inconvenience in subsequent transferring and packaging, and easiness in damaging the health of workers due to long-time repeated labor. In order to solve the problems of low manual efficiency and slow typesetting speed, a plurality of enterprises begin to adopt mechanical technology to laminate.
At present, lamination machines have more related technologies, but lamination machines directly applicable to prepregs still have less technologies. Huang Cheng, zhu Changneng et al describe a pallet changer and an automatic prepreg stacking system in the utility model patent of pallet changer and automatic prepreg stacking system, wherein the prepreg stacking device lacks a calibration mechanism, and if there is an error in prepreg transfer and prepreg suction, the prepreg is easy to be placed unevenly, the stack is inclined, and the prepreg is unstable.
Besides the lamination machine technology directly applied to prepregs, lamination machine technical materials in other industries are more. In the patent He Lin of the utility model, "a lithium battery cell lamination system", a necessary procedure in the lithium battery industry is to stack pole pieces, but the existing lamination machine technology is easy to shift in the process of transmitting the pole pieces, so that the alignment precision is low after stacking is finished, the generated cell is poor, and the process requirement is difficult to meet; in the patent of Liang Jian, liang Jinpei et al, a lamination machine, protective film paper is added between each glass sheet through the glass lamination machine, but the device lacks an accurate alignment system, if the suction and the discharge are improper, the glass stack is easy to collapse, and economic loss is caused; in the patent of the utility model of the Mild east, namely a lamination machine and a lamination method, the lamination machine shortens the auxiliary blanking time of the battery cells through the cross transposition of the mechanism, but the lamination machine still lacks a sheet calibration mechanism, so that the mechanism is inaccurate in blanking, the error rate of a finished product is high, and the loss is easy to generate.
As described above, the existing lamination machine system has the problem of lacking a sheet calibration mechanism, so that the prepreg stacking is easy to be out of order, the stacking is easy to be out of order, and the sheet collapses, so that economic loss is caused.
Disclosure of Invention
The utility model aims to solve the technical problem of irregular stacking caused by the lack of a sheet calibration mechanism of the existing lamination machine, and provides a lamination machine based on machine vision, a sheet calibration method and a control method thereof.
In one aspect, the utility model provides a sheet calibration method of a lamination machine based on machine vision, which comprises the following steps:
step 1: acquiring an image of a manipulator material taking mechanism grabbing a sheet material in a visual alignment area;
step 2: identifying the sheet material area of the image in the step 1 to obtain a sheet material area image, and performing edge detection to obtain an edge image of the sheet material;
step 3: detecting the longest straight line in the edge image by adopting Hough transformation, and calculating a rotation angle based on the longest straight line;
step 4: rotating the center point of the image in the step 1 based on the rotation angle to obtain a plane image;
step 5: inputting the plane image obtained in the step 4 into a trained yolo3 network to obtain sheet target point coordinates;
the yolo3 network is trained by sheet material images and four corner coordinate points of a sheet material positioning frame in a standard state, wherein the sheet material images are original grabbing images or sheet material area images identified by sheet material areas, and sheet material target point coordinates can be calculated based on the four corner coordinate points of the sheet material positioning frame;
step 6: controlling the rotation and movement of the manipulator material taking mechanism by using the rotation angle in the step 3 and the transverse-longitudinal distance between the coordinates of the sheet material target point and the standard target point in the step 5, and further stacking the sheet materials into a stacking area;
and selecting a sheet target point of any sheet image in a standard state in the target stacking area as the standard target point.
It will be appreciated that the target point is preferably a centre point and that other positions, which are easily located, may be set as target points in other possible ways.
According to the sheet calibration method provided by the utility model, the Yolo3 network is combined with the Hough transformation, the Hough transformation is utilized to solve the rotation angle (deflection angle), so that the sheet image is adjusted, the Yolo3 network is utilized to position the adjusted sheet image to obtain the center point coordinate of the sheet, the center point coordinate is further compared with the standard center point to obtain the transverse and longitudinal offset of the sheet, and finally, the control and adjustment are performed based on the transverse and longitudinal offset and the deflection angle, so that the sheet grabbed by the manipulator material taking mechanism can be aligned accurately. It should be understood that the standard center point is taken as the calibration position, which is considered as the sheet center point coordinate that meets the stacking requirements.
In this case, when stacking is performed for the first time for the finished product, it is necessary to perform center coordinate calibration (initialization), that is, determine the coordinates of the target point of the tablet by using the standard image. It should be appreciated that initialization may also utilize the yolo3 network training image as a standard image.
Optionally, the step 2 of obtaining the sheet area image is to convert the image in step 1 from RGB color space to HSV color space, and then obtain the sheet area through HSV color space filtering.
Optionally, the training process of the yolo3 network is:
firstly, adjusting the sheet materials to a standard state in a stacking area, and then acquiring a plurality of standard images of the sheet materials captured by a mechanical arm material taking mechanism;
then, identifying a sheet material area of the standard image to obtain a sheet material area image, and determining four corner coordinate points of a sheet material positioning frame, namely four corner coordinates of the sheet material;
finally, training the yolo3 network based on a plurality of sheet area images or the plurality of standard images and four corner coordinate points of the sheet positioning frame corresponding to the standard images;
the input of the yolo3 network is a sheet material area image or an original grabbing image, and the output of the yolo3 network is a sheet material positioning frame determined by four-corner coordinates, wherein the output of the yolo3 network is a rectangular frame, but the rectangular frame is also determined according to the four-corner coordinates.
It should be understood that the training image of the training process is an additionally collected standard image as the training image.
In a second aspect, the utility model provides a lamination machine based on machine vision, which is provided with a sheet calibration subsystem, wherein the sheet calibration subsystem comprises a camera arranged above a stacking area and an industrial personal computer in communication connection with the camera;
and loading or calling a program of the sheet calibration method in the industrial personal computer, and finally controlling the movement and rotation of the manipulator material taking mechanism so as to stack the sheets in a stacking area.
Optionally, the lamination machine further includes at least: a sheet lifting table; the sheet lifting table comprises a sheet lifting area and a finished product lifting area, and the finished product lifting area is a stacking area;
the automatic lifting device comprises a finished product lifting platform, a sheet lifting area, an industrial personal computer, a sheet lifting area and a finished product lifting area, wherein the lifting platform mechanisms of the sheet lifting area and the finished product lifting area are both in communication connection with the industrial personal computer, and the industrial personal computer controls the lifting platform mechanisms to realize automatic lifting of the sheet lifting area and automatic descending of the finished product lifting platform, so that the material taking height on the sheet lifting area is consistent with the material discharging height on the finished product lifting area;
wherein the sheet lifting areas are divided according to sheet types, and each type of sheet corresponds to one sheet lifting area.
The utility model always keeps the height consistency of material taking and discharging, can make the mechanical manual work circulation consistent, and greatly improves the typesetting efficiency of the lamination. For example, the sheet lifting area is lifted by one sheet height after each material taking, and the finished product lifting area is lifted by one sheet height after each lamination, so that the material taking height on the sheet lifting area is ensured to be consistent with the discharging height on the finished product lifting area.
Optionally, the lifting platform mechanism comprises a lifting platform, a guide rod arranged on the side edge of the lifting platform and a servo lifting mechanism, wherein the servo lifting mechanism is used for driving the lifting platform to lift along the guide rod;
and/or a speed doubling chain and/or a blocking mechanism are arranged on the lifting table of the sheet lifting area, and the blocking mechanism is positioned on the boundary of the material taking area on the lifting table and used for blocking the material tray; the speed-doubling chains are arranged on two sides of the material taking area, and the trays for placing the sheets are conveyed to the material taking area through the speed-doubling chains.
And/or the support of the sheet lifting area and the finished product lifting area is provided with a super-strong ion wind bar and/or a brush anti-carrying mechanism, and the support bears a lifting table in the lifting platform mechanism.
On the basis of the lifting platform mechanism, the utility model has no specific requirements on the lifting platform provided with the double-speed chain, the blocking mechanism, the support provided with the super-strong ion wind bar, the brush material-carrying prevention mechanism and the like, i.e. the structures can not be simultaneously arranged on the same lamination machine.
Optionally, the lamination machine further includes at least: the manipulator feeding mechanism is connected with the feeding manipulator moving mechanism and the manipulator feeding mechanism connected with the feeding manipulator moving mechanism, and the feeding manipulator moving mechanism drives the manipulator feeding mechanism to realize movement in the transverse direction x, the longitudinal direction y and the height direction z and rotation of the R shaft.
Optionally, a servo driving mechanism for realizing transverse movement is arranged in the material taking manipulator moving mechanism, and comprises a servo motor guide rail and a servo motor, wherein a bracket where the manipulator material taking mechanism is arranged on the servo motor guide rail, and the manipulator material taking mechanism is controlled to realize transverse movement under the action of the servo motor guide rail and the servo motor;
and/or a lifting cylinder is arranged in the material taking mechanical arm moving mechanism, and the lifting cylinder is arranged on a bracket where the material taking mechanical arm is located and is connected with the material taking mechanical arm to control the material taking mechanical arm to move in the height direction z;
and/or the material taking mechanism is provided with a DD motor, and the DD motor is arranged on a bracket where the material taking mechanism is arranged and is connected with the material taking mechanism and used for controlling the material taking mechanism to realize the rotation of an R shaft;
and/or a servo driving mechanism for realizing longitudinal movement is arranged in the material taking mechanical arm moving mechanism, and the servo driving mechanism for longitudinal movement is arranged on a bracket where the material taking mechanical arm is arranged and is connected with the material taking mechanical arm and used for controlling the material taking mechanical arm to realize longitudinal movement.
In the material taking manipulator moving mechanism, the utility model has no specific requirement on whether the servo driving mechanism for realizing transverse movement, the lifting cylinder, the DD motor and the servo driving mechanism for realizing longitudinal movement are the structures at the same time, namely the structures can be arranged on the same lamination machine at different times, and partial functions can be replaced by other structures.
Optionally, the manipulator extracting mechanism at least comprises a suction nozzle, a color code sensor and a guide rail;
wherein the guide rail comprises a transverse guide rail and a longitudinal guide rail which are in connection, so that the longitudinal guide rail provided with the suction nozzle can be transversely adjusted along the transverse guide rail.
In a third aspect, the present utility model further provides a control method based on the lamination machine, which includes:
acquiring next sheet information according to the stacking requirement of the finished product;
according to the next sheet material information, controlling a manipulator material taking mechanism to take materials on a material taking area corresponding to a sheet material lifting area, and then controlling the sheet material lifting area to ascend;
the mechanical arm material taking mechanism is controlled to stack the grabbed sheet materials to a finished product lifting area, and then the cost lifting area is controlled to descend; the sheet calibration method is used for realizing accurate stacking, and controlling the material taking height on the sheet lifting area to be consistent with the material discharging height on the finished product lifting area;
the above process is cycled until the finished product stack is completed.
Optionally, the method further comprises: if the material in the material taking area on the material lifting area is detected to be used up, a signal is sent to inform the RGV trolley of transporting the empty material tray for replacing the material plate and conveying the material tray to the material taking area. Or as follows: and sending a signal to inform the RGV trolley of transporting the empty tray in advance for replacing the material plates when one sheet typesetting is about to be finished, so that the efficiency of the lamination machine is further improved.
Advantageous effects
1. The utility model provides a sheet calibration method of a lamination machine based on machine vision, which is applied to the lamination machine, combines a Yolo3 network and Hough transformation, solves a rotation angle (deflection angle) by using the Hough transformation, adjusts a sheet image, positions the adjusted sheet image by using the Yolo3 network to obtain a sheet center point coordinate, compares the sheet center point coordinate with a standard center point to obtain a transverse and longitudinal offset of a sheet, and finally controls and adjusts the sheet based on the transverse and longitudinal offset and the deflection angle, so that the sheet grabbed by a manipulator material taking mechanism can be aligned accurately, and the problem that the existing lamination machine system lacks a sheet calibration mechanism is effectively solved. In particular, the sheet calibration method can be applied to various lamination machines, has a wide application range, and is more suitable for lamination machines in the field of prepregs.
2. According to the lamination machine provided by the utility model, the automatic lifting of the sheet lifting area and the automatic lowering of the finished product lifting table are realized by means of automatic control, so that the material taking height on the sheet lifting area is consistent with the material discharging height on the finished product lifting area, the mechanical manual operation is consistent in circulation, and the typesetting efficiency of lamination is greatly improved.
Drawings
Fig. 1 is a schematic structural view of a lamination machine provided by the present utility model;
FIG. 2 is a schematic diagram of a movement mechanism of a material taking manipulator provided by the utility model;
FIG. 3 is a schematic view of a reclaimer mechanism of the reclaiming robot;
fig. 4 is a schematic structural view of the sheet lifting platform provided by the utility model;
fig. 5 is a schematic flow chart of a control method of the lamination machine provided by the utility model;
fig. 6 is a schematic flow chart of a sheet calibration method of a lamination machine based on machine vision provided by the utility model;
FIG. 7 is a flowchart of a Canny edge detection algorithm;
FIG. 8 is a partial schematic diagram of a Canny edge detection algorithm, wherein (a) is a schematic diagram of all gradient angles being discretized into four sectors; (b) is a suppression window schematic;
FIG. 9 is a schematic diagram of a hough transform process;
the reference numerals are explained as follows:
1-A material lifting table, 2-B material lifting table, 3-finished product lifting table, 4-electric control cabinet, 5-A sheet taking manipulator, 6-B sheet taking manipulator, 7-CCD camera, 8/13-man-machine interface, 9-safety grating, 10-protective cover, 11-alarm lamp, 12-air source triple piece, 14-servo motor, 15-servo motor guide rail, 16-lifting cylinder, 17-DD motor, 18-flexible anticollision mechanism, 19-color scale sensor, 20-super ion wind bar, 21-brush anti-carrying mechanism, 22-double speed chain, 23-blocking mechanism, 24-servo motor, 25-stacking area, 26-A sheet taking area, 27-B sheet taking area, 28-height sensor and 29-servo lifting mechanism.
Detailed Description
The utility model provides a lamination machine based on machine vision, which introduces a sheet calibration method of the lamination machine based on machine vision, is used for solving the sheet calibration problem in the lamination process, can be applied to various types of sheets, and the following embodiment will take prepreg as an example. In addition, the lamination machine based on machine vision provided by the utility model is provided with a set of complete structure for automatic control, but the replacement or deletion of part of elements and structures on the basis of not deviating from the concept of the utility model also belongs to the protection scope of the utility model.
The utility model will be further illustrated with reference to examples.
Example 1:
as shown in fig. 1, the present embodiment provides a lamination machine based on machine vision, which includes: the device comprises a sheet material lifting table, a material taking manipulator moving mechanism, a manipulator material taking mechanism, a CCD camera 7, a protective cover 10, an air source triplet 12, a safety grating 9, an alarm lamp 11, an electric control cabinet 4 and a human-computer interface 8/13.
Wherein, the sheet material lifting platform comprises a sheet material lifting area and a finished product lifting area (a finished product lifting platform), and each type of sheet material corresponds to one sheet material lifting area. In this embodiment, the sheet types include a type a sheet (a prepreg) and a type B sheet (B prepreg), and thus, a material lifting area (a material lifting table 1) and a material lifting area (B material lifting table 2) are correspondingly provided, and a finished product lifting table 3 is located between the a material lifting table 1 and the B material lifting table 2 for stacking the a material and the B material of a fixed formulation.
All be equipped with the lift platform mechanism who is connected with the industrial computer on material elevating platform 1, material elevating platform 2, the finished product elevating platform 3, the industrial computer is in order to realize the automatic rising of sheet material elevating area (material elevating platform 1, material elevating platform 2) and the automatic decline of finished product elevating platform 3 through control elevating platform mechanism, promptly can go on automatic rising after the material is got to material district and material district is got to the B piece after once getting, pile up district 25 and can go on the decline automatically after accepting any sheet material in material district 26 and the material district 27 is got to the A piece for get the material height in the material elevating district and the blowing height in the finished product elevating district is unanimous. As shown in fig. 4, three lifting platform mechanisms are arranged on the sheet lifting platform in this embodiment, and correspond to the material lifting platform 1, the material lifting platform 2 and the finished product lifting platform 3 respectively, each lifting platform mechanism comprises a lifting platform, 4 guide rods arranged on the side edges of the lifting platform, and a servo lifting mechanism 29, and the servo lifting mechanism 29 is used for driving the lifting platform to lift along the guide rods. In this embodiment, the servo lifting mechanism 29 is a driving structure disposed on two sides of the lifting platform, and adopts a structural design of a servo motor 24+screw rod, so as to ensure stable lifting of the lifting platform.
As shown in fig. 4, in this embodiment, a super ion wind bar 20 and a brush anti-carrying mechanism 21 are disposed on the side of each sheet lifting area (a lifting table 1, B lifting table 2) and the support of the product lifting area. Wherein the super ion wind bar 20 generates a large amount of air mass with positive and negative charges to neutralize the charges on the sheet material so as to eliminate static electricity and prevent the sheet material from being carried. When the material is taken, the brush anti-carrying mechanism 21 eliminates static electricity for the sheet again, so that the sheet is prevented from being carried by the material when the sheet is sucked by the matching manipulator, and secondary anti-carrying protection is realized.
In this embodiment, a double speed chain 22 and a blocking mechanism 23 are provided on the lift table of each sheet lift region (the material lift table 1, the material lift table 2). When the RGV trolley conveys the feeding tray to the lifting table, the feeding tray is gradually moved to a material taking area through the double-speed chain 22, and finally, the feeding tray is stopped through the blocking mechanism 23; the feeding direction refers to the moving direction when the feeding tray of the RGV trolley moves through the double speed chain 22.
In addition, the sheet lifting table in this embodiment is further provided with a height sensor 28 for achieving height information collection.
In this embodiment, the material taking manipulator moving mechanism of the lamination machine is in communication connection with the industrial personal computer, and the material taking manipulator moving mechanism is connected with the manipulator material taking mechanism and is used for driving the manipulator material taking mechanism to realize movement of transverse x, longitudinal y and height direction z and rotation of the R shaft. The material lifting and lowering device comprises a material lifting and lowering table A, a material lifting and lowering table B, a material lifting and lowering mechanism A, a material lifting and lowering mechanism B and a material lifting and lowering mechanism B, wherein the material lifting and lowering mechanisms A, 5 and 6 are respectively used for realizing material lifting and discharging between the material lifting and lowering table A1 and a finished product lifting and lowering table 3, and material lifting and lowering between the material lifting and lowering table B2 and the finished product lifting and lowering table 3.
As shown in fig. 2, the material taking manipulator moving mechanism comprises a servo driving mechanism for realizing transverse movement, a lifting cylinder 16, a DD motor 17, a servo driving mechanism for realizing longitudinal movement and a manipulator fool-proof sensor.
The servo driving mechanism for realizing the transverse movement comprises a servo motor guide rail 15 and servo motors 14 on two sides of the servo motor guide rail 15, wherein a bracket where the manipulator material taking mechanism is arranged on the servo motor guide rail 15, and the manipulator material taking mechanism is controlled to realize the transverse x-axis movement under the action of the servo motor guide rail 15 and the servo motors 14. As shown in fig. 2, the brackets of the a-piece material taking manipulator 5 and the B-piece material taking manipulator 6 in the embodiment are both arranged on the servo motor guide rail 15.
The lifting cylinder 16, the DD motor 17 and the servo driving mechanism for realizing longitudinal movement are arranged on the support of the A-piece material taking manipulator 5 and the B-piece material taking manipulator 6, so that the lifting cylinder 16, the DD motor and the servo driving mechanism for realizing longitudinal movement are arranged on the A-piece material taking manipulator 5 and the B-piece material taking manipulator 6. In the embodiment, a lifting cylinder 16 is arranged above each manipulator, so that the manipulator can move on the Z axis; each manipulator is also provided with a DD motor 17 and a servo motor above it for Y-axis displacement of the manipulator, the DD motor 17 enabling the manipulator to move on the R-axis. And the manipulator foolproof induction is arranged between the A-piece material taking manipulator 5 and the B-piece material taking manipulator 6, so that mutual collision is avoided, and the mechanical life is lost.
As shown in fig. 3, the structure of the sheet a material taking manipulator 5 is the same as that of the sheet B material taking manipulator 6, the sheet a material taking manipulator 5 and the sheet B material taking manipulator 6 comprise a suction nozzle, a guide rail, a color code sensor 19 arranged at the bottom and a flexible anti-collision mechanism 18, the color code sensor 19 is used for sensing whether sheet materials with corresponding colors exist below, if not, a material shortage signal is sent, and the flexible anti-collision sensor 18 is used for detecting that the sheet materials are reached or collide with an obstacle so as to prevent the mechanical structure from being damaged due to excessive descent of the manipulator. The lower part of the manipulator is provided with a transverse guide rail and a longitudinal guide rail which have a connection relationship, in the embodiment, a pair of transverse guide rails are arranged, two ends of the transverse guide rail are respectively provided with a pair of parallel longitudinal guide rails, and a suction nozzle is hung on the longitudinal guide rails, and the longitudinal sliding can move transversely along the transverse guide rails, so that the distance between the suction nozzles on each side of the two longitudinal guide rails is adjustable; the distance between the suction nozzles between the sliding rails at the two sides is also adjustable, so that the optimal adsorption points can be conveniently selected in the debugging process. The present utility model is not limited to this, and the present utility model can realize the transverse movement of the longitudinal rail by the existing precise control technology of the machine. In addition, the protective cover 10 on the lamination machine of the embodiment is arranged above the whole system and on the left and right sides for dust prevention and protection; the air source triple piece 12 is arranged on the side surface of the system and is used for stabilizing pressure, cleaning and lubricating an air source; the safety grating 9 is positioned below the front side protective cover 10, so that workers are prevented from approaching the mobile machinery, and casualties are avoided; the alarm lamp 11 is arranged at the corner of the protective cover 10 and is used for alarming faults; the electric control cabinet 4 is arranged below the rear side protective cover 10 and is used for controlling the power supply of the whole system, and in the embodiment, the industrial personal computer is positioned in the electric control cabinet 4 to realize the automatic control of the lamination machine; the human-computer interface 8/13 is arranged on the side surface of the system and used for human-computer interaction.
The CCD camera 7 on the lamination machine of this embodiment is fixed on the beam above the finished product lifting table 3, and is connected with the industrial personal computer, and is used for collecting sheet material images, and transmitting the sheet material images to the industrial personal computer, and the sheet material calibration method is loaded or called in the industrial personal computer to run, so as to finally control the movement and rotation of the sheet material taking manipulator 5 and the sheet material taking manipulator 6, and further neatly stack the sheet a and the sheet B in the stacking area 25.
According to the sheet calibration method of the lamination machine based on machine vision, a Yolo3 network and Hough transformation are combined, a rotation angle (deflection angle) is solved by using the Hough transformation, and a sheet center point coordinate is obtained by using the Yolo3 network. Wherein, for sheet stacking of any finished product, initialization setting and prior Yolo3 network training are required. The visual alignment system is initialized as follows:
and (3) orderly placing the sheet materials on the finished product lifting table 3, manually adjusting the directions of the light source and the camera, and manually controlling the mechanical arm to suck the sheet materials of the finished product lifting table 3 so as to obtain the most standard grabbing image. Similarly, before the Yolo3 network training is performed in this embodiment, a plurality of most standard captured images may be obtained through multiple photographing as training images.
The sheet stock can be ensured to be placed in the finished product lifting table in a standard mode through manual adjustment, but before being placed in the finished product lifting table, the camera can shoot standard images, and therefore the shot standard images are images which are grabbed above the finished product lifting table.
Calculating color information, saturation and brightness of the standard image in the HSV color space according to a conversion calculation formula from the RGB color space to the HSV color space, wherein the conversion calculation formula is shown in the following formulas (1) - (3);
identifying the material plate area according to the calculated color information, saturation and brightness to obtain a sheet material area image;
the center point position of the sheet is then calculated.
The yolo3 network training process is to input a plurality of sheet material area images or a plurality of standard images corresponding to the standard images and sheet material positioning frames corresponding to four-corner coordinate points of the sheet materials into the yolo3 network for training; the input data of the yolo3 network is a sheet area image or an original grabbing image, the output data is a sheet positioning frame, four-angle coordinate points can be further determined based on the sheet positioning frame, and then a sheet center point is determined.
In this embodiment, considering that the capturing of the sheet is not a certain standard, the light irradiation causes an increase and decrease in the saturation and brightness of the image, and the upper and lower ranges of the saturation and brightness ranges are respectively enlarged by 5 according to the HSV color space table described below to ensure the filtering effect thereafter. Taking a plate material as yellow as an example, the color information H is between 26 and 34, the saturation value S is between 100 and 255, the brightness V is between 100 and 255, the upper and lower measuring ranges of the saturation and brightness range are respectively enlarged by 5, and then the yellow material plate area can be effectively identified according to the actually calculated color information, saturation and brightness.
In the formula, R, G, B is an image of an R channel, a G channel and a B channel obtained after capturing a color image for decomposition, H is color information, S is saturation, and V is a bright range.
HSV color space table:
and calculating the coordinates of the center point of the sheet material based on the sheet material positioning frame corresponding to the sheet material image of the trained yolo3 network output plane and the four-corner coordinate points. As shown in fig. 6, a sheet calibration method of a lamination machine based on machine vision includes the following steps:
step 1: and acquiring an image of the sheet material captured by the manipulator material taking mechanism in the visual alignment area. Wherein the above-mentioned initialization operation is required for the first stacking.
Step 2: identifying the sheet material area of the image in the step 1 to obtain a sheet material area image, and performing edge detection to obtain an edge image of the sheet material;
if the A piece is grabbed to the vision alignment area, a sheet material image is acquired through a CCD camera 7, the image is copied, HSV color space conversion is carried out on the copied image according to the formulas (1) - (3), and then HSV filtering is carried out by combining an HSV color space table and a standard grabbing plate image to obtain the sheet material area.
In the embodiment, a Canny edge detection algorithm is adopted for the sheet area image to obtain an edge image of the sheet; as shown in fig. 7, the implementation procedure of the Canny edge detection algorithm is briefly described as follows:
step 2.1, smoothing the detected edge image by using a Gaussian filter;
the gaussian filter kernel is shown as formula (4), the specific filtering process is shown as formula (5), g (x, y) is a smoothed image, f (x, y) is a pre-smoothed image, sigma is a gaussian filter parameter, sigma is larger, the action range is larger, the image is blurred, wherein x represents convolution calculation, and x, y are pixel coordinates:
g(x,y)＝h(x,y,σ)*f(x,y) (5)
step 2.2, calculating the amplitude and direction of the image gradient by adopting the finite difference of the first-order partial derivatives;
wherein, the image g (x, y) is convolved by utilizing two differential convolution operators to obtain the imageOffset arrays f 'for both x and y' x (x, y) and f' y (x, y), wherein:
f′ x (x,y)＝[f(x+1,y)-f(x,y)+f(x+1,y+1)-f(x,y+1)]/2 (6)
f′ y (x,y)＝[f(x,y+1)-f(x,y)+f(x+1,y+1)-f(x+1,y)]/2 (7)
the image edge angle and edge direction can be represented by M and Θ:
θ[x,y]＝arctan(f′ x (x,y)/f′ x (x,y)) (9)
step 2.3, performing non-maximum suppression on the gradient amplitude, dispersing all gradient angles into four sectors, and performing suppression operation by using a 3×3 window, wherein the suppression window is shown in fig. 8 (b). For example, when it is known that the edge direction of a certain point is 75 degrees and is within the range 2 through the step 3.2, the pixel point is compared with the maximum value between 2 and 6, if yes, the point is an edge point, and if not, the point is not an edge point.
And 2.4, finally detecting and connecting edges by using a double-threshold algorithm.
Step 3: and detecting the longest straight line in the edge image by adopting Hough transformation on the edge image, and calculating the rotation angle based on the longest straight line.
The Hough transform process is shown in fig. 9. Each point in space has n straight lines passing through the point, and all straight line parameters passing through the point satisfy the equation xcos theta + ysin theta = p, where theta represents the normal angle of the straight line and p represents the distance from the origin to the straight line. The equation is a trigonometric function curve in the parameter space, and if the points in the image space are on a straight line, the trigonometric function also intersects the same point in the parameter space, so that the problem of straight line detection is converted into the problem of solving a common point of the curve. Therefore, the longest straight line shared by the straight line equations is found, and the deflection angle of the sheet material can be calculated by utilizing the formula.
Step 4: and (3) rotating the center point of the image in the step (1) based on the rotation angle to obtain a plane image. The original image is selected to rotate, and the original image is changed in consideration of the follow-up operations such as copying, HSV space conversion, linear detection and the like.
The original image size is adopted after rotation, and the empty space is supplemented with white.
Step 5: and (3) inputting the plane image obtained in the step (4) into a trained yolo3 network to obtain the coordinates of the sheet target point.
Step 6: and (3) controlling the movement and rotation of the manipulator taking mechanism by using the transverse and longitudinal distance between the coordinates of the sheet target point in the step (5) and the standard target point and the rotation angle in the step (3), and further stacking the sheets in a stacking area.
The manipulator is controlled to rotate along the R axis by an angle theta (rotation angle), and then is controlled to shift an X distance (a transverse distance X between the coordinates of the sheet target point and the standard target point) along the X axis direction and a Y distance (a longitudinal distance Y between the coordinates of the sheet target point and the standard target point) along the Y axis direction. It should be understood that the calculated lateral-longitudinal distance has a positive or negative score corresponding to the offset direction of the control manipulator.
Based on the lamination machine and the sheet calibration method, the utility model also provides a control method based on the lamination machine, which comprises the following steps:
acquiring next sheet information according to the stacking requirement of the finished product;
according to the next sheet material information, controlling a manipulator material taking mechanism to take materials on a material taking area corresponding to a sheet material lifting area, and then controlling the sheet material lifting area to ascend;
the mechanical arm material taking mechanism is controlled to stack the grabbed sheet materials to a finished product lifting area, and then the cost lifting area is controlled to descend; the sheet calibration method is used for realizing accurate stacking, and controlling the material taking height on the sheet lifting area to be consistent with the material discharging height on the finished product lifting area;
the above process is cycled until the finished product stack is completed.
Fig. 5 shows a process of taking a sheet a and a sheet B in this embodiment. Specifically, the process of taking a piece A is considered as follows: and (3) taking the A piece: detecting whether the material lifting table 1 has materials or not, grabbing and stacking if the materials exist, triggering the material feeding signal A if the materials do not exist, taking materials by the material taking manipulator 5, conveying the materials to the finished product lifting table 3, and controlling the material lifting table 1 to ascend and the finished product lifting table 3 to descend; the A-piece taking manipulator 5 returns to take the A-piece and waits; the finished product lifting table 3 detects whether the material is fully piled, and the material plate is replaced when the material is fully piled.
And if the sheet materials are used up, sending a signal to inform the RGV trolley of transporting the empty tray for replacing the material plates and conveying the material plates to the material taking area.
It should be understood that the sheet calibration method of the machine vision-based lamination machine provided by the utility model can be applied to other types of sheet materials, and part of structures of the lamination machine provided by the utility model can be selected to replace or subtract part of structures, so that part of functions are lost. On the basis of not deviating from the concept of the utility model, the structure of the lamination machine and the adaptability adjustment of the sheet calibration method and the control method provided by the utility model are considered to fall into the protection scope of the utility model.
It should be emphasized that the examples described herein are illustrative rather than limiting, and that this utility model is not limited to the examples described in the specific embodiments, but is capable of other embodiments in accordance with the teachings of the present utility model, as long as they do not depart from the spirit and scope of the utility model, whether modified or substituted, and still fall within the scope of the utility model.
Claims (10)
1. A sheet calibration method of a lamination machine based on machine vision is characterized by comprising the following steps: the method comprises the following steps:
step 1: acquiring an image of a manipulator material taking mechanism grabbing a sheet material in a visual alignment area;
step 2: identifying the sheet material area of the image in the step 1 to obtain a sheet material area image, and then carrying out edge detection to obtain an edge image of the sheet material;
step 3: detecting the longest straight line in the edge image by adopting Hough transformation, and calculating a rotation angle based on the longest straight line;
step 4: rotating the center point of the image in the step 1 based on the rotation angle to obtain a plane image;
step 5: inputting the plane image obtained in the step 4 into a trained yolo3 network to obtain sheet target point coordinates;
the yolo3 network is trained by sheet material images and four corner coordinate points of a sheet material positioning frame in a standard state, and sheet material target point coordinates can be calculated based on the four corner coordinate points of the sheet material positioning frame;
step 6: controlling the rotation and movement of the manipulator material taking mechanism by using the rotation angle in the step 3 and the transverse-longitudinal distance between the coordinates of the sheet material target point and the standard target point in the step 5, and further stacking the sheet materials into a stacking area; and selecting a sheet target point of any sheet image in a standard state in the target stacking area as the standard target point.
2. The machine vision-based sheet calibration method of a lamination machine of claim 1, wherein: the step 2 of obtaining the sheet material area image is to convert the image in the step 1 from RGB color space to HSV color space and then obtain the sheet material area image through HSV color space filtering.
3. The machine vision-based sheet calibration method of a lamination machine of claim 1, wherein: the training process of the yolo3 network is as follows:
firstly, adjusting the sheet materials to a standard state in a stacking area, and then acquiring a plurality of standard images of the sheet materials captured by a mechanical arm material taking mechanism;
then, identifying a sheet material area of the standard image to obtain a sheet material area image, and determining four corner coordinate points of a sheet material positioning frame;
finally, training the yolo3 network based on a plurality of sheet area images or the plurality of standard images and four corner coordinate points of the sheet positioning frame corresponding to the standard images;
the input of the yolo3 network is a sheet material area image or an original grabbing image, and the output of the yolo3 network is a sheet material positioning frame determined by four-angle coordinates.
4. Lamination machine based on machine vision, its characterized in that: the device is provided with a sheet calibration subsystem, wherein the sheet calibration subsystem comprises a camera arranged above a stacking area and an industrial personal computer in communication connection with the camera;
the process of loading or calling the sheet calibration method of any one of claims 1-3 in the industrial personal computer, and finally controlling the movement and rotation of the manipulator material taking mechanism, so as to stack the sheets in the stacking area.
5. The lamination machine of claim 4, wherein: also at least comprises: a sheet lifting table; the sheet lifting table comprises a sheet lifting area and a finished product lifting area, and the finished product lifting area is a stacking area;
the automatic lifting device comprises a finished product lifting platform, a sheet lifting area, an industrial personal computer, a sheet lifting area and a finished product lifting area, wherein the lifting platform mechanisms of the sheet lifting area and the finished product lifting area are both in communication connection with the industrial personal computer, and the industrial personal computer controls the lifting platform mechanisms to realize automatic lifting of the sheet lifting area and automatic descending of the finished product lifting platform, so that the material taking height on the sheet lifting area is consistent with the material discharging height on the finished product lifting area;
wherein the sheet lifting areas are divided according to sheet types, and each type of sheet corresponds to one sheet lifting area.
6. The lamination machine of claim 5, wherein: the lifting platform mechanism comprises a lifting platform, a guide rod arranged on the side edge of the lifting platform and a servo lifting mechanism, wherein the servo lifting mechanism is used for driving the lifting platform to lift along the guide rod;
and/or a speed doubling chain and/or a blocking mechanism are arranged on the lifting table of the sheet lifting area, and the blocking mechanism is positioned on the boundary of the material taking area on the lifting table and used for blocking the material tray; the speed-doubling chains are arranged on two sides of the material taking area, and a tray for placing sheets is conveyed to the material taking area through the speed-doubling chains;
and/or the support of the sheet lifting area and the finished product lifting area is provided with a super-strong ion wind bar and/or a brush anti-carrying mechanism, and the support bears a lifting table in the lifting platform mechanism.
7. The lamination machine of claim 4, wherein: also at least comprises: the manipulator feeding mechanism is connected with the feeding manipulator moving mechanism and the manipulator feeding mechanism connected with the feeding manipulator moving mechanism, and the feeding manipulator moving mechanism drives the manipulator feeding mechanism to realize movement in the transverse direction x, the longitudinal direction y and the height direction z and rotation of the R shaft.
8. The lamination machine of claim 7, wherein: the manipulator feeding mechanism comprises a manipulator feeding mechanism, a feeding mechanism and a feeding mechanism, wherein a servo driving mechanism for realizing transverse movement is arranged in the manipulator feeding mechanism, the servo driving mechanism comprises a servo motor guide rail and a servo motor, a bracket where the manipulator feeding mechanism is arranged on the servo motor guide rail, and the manipulator feeding mechanism is controlled to realize transverse movement under the action of the servo motor guide rail and the servo motor;
and/or a lifting cylinder is arranged in the material taking mechanical arm moving mechanism, and the lifting cylinder is arranged on a bracket where the material taking mechanical arm is located and is connected with the material taking mechanical arm to control the material taking mechanical arm to move in the height direction z;
and/or the material taking mechanism is provided with a DD motor, and the DD motor is arranged on a bracket where the material taking mechanism is arranged and is connected with the material taking mechanism and used for controlling the material taking mechanism to realize the rotation of an R shaft;
and/or a servo driving mechanism for realizing longitudinal movement is arranged in the material taking mechanical arm moving mechanism, and the servo driving mechanism for longitudinal movement is arranged on a bracket where the material taking mechanical arm is arranged and is connected with the material taking mechanical arm and used for controlling the material taking mechanical arm to realize longitudinal movement.
9. The lamination machine of claim 7, wherein: the manipulator material taking mechanism at least comprises a suction nozzle, a color code sensor and a guide rail;
the guide rail comprises a transverse guide rail and a longitudinal guide rail which are in connection, the longitudinal guide rail is arranged at two ends of the transverse guide rail, and the longitudinal guide rail provided with the suction nozzle can transversely slide along the transverse guide rail.
10. A control method based on the lamination machine of claim 4, characterized in that: comprising the following steps:
acquiring next sheet information according to the stacking requirement of the finished product;
according to the next sheet material information, controlling a manipulator material taking mechanism to take materials on a material taking area corresponding to a sheet material lifting area, and then controlling the sheet material lifting area to ascend;
the mechanical arm material taking mechanism is controlled to stack the grabbed sheet materials to a finished product lifting area, and then the finished product lifting area is controlled to descend; the sheet calibration method is used for realizing accurate stacking, and controlling the material taking height on the sheet lifting area to be consistent with the material discharging height on the finished product lifting area;
the above process is cycled until the finished product stack is completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111166209.1A CN114056920B (en) | 2021-09-30 | 2021-09-30 | Lamination machine based on machine vision and sheet calibration method and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111166209.1A CN114056920B (en) | 2021-09-30 | 2021-09-30 | Lamination machine based on machine vision and sheet calibration method and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114056920A CN114056920A (en) | 2022-02-18 |
| CN114056920B true CN114056920B (en) | 2023-05-05 |
Family
ID=80234149
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111166209.1A Active CN114056920B (en) | 2021-09-30 | 2021-09-30 | Lamination machine based on machine vision and sheet calibration method and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114056920B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117048960A (en) * | 2023-10-11 | 2023-11-14 | 广东龙丰精密铜管有限公司 | Pipe packaging method, control device, intelligent pipe packaging device and medium |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2935847B2 (en) * | 1989-02-07 | 1999-08-16 | 本田技研工業株式会社 | Image processing device |
| GB0405014D0 (en) * | 2004-03-05 | 2004-04-07 | Qinetiq Ltd | Movement control system |
| JP4659631B2 (en) * | 2005-04-26 | 2011-03-30 | 富士重工業株式会社 | Lane recognition device |
| CN104058260B (en) * | 2013-09-27 | 2016-07-20 | 沈阳工业大学 | The robot automatic stacking method that view-based access control model processes |
| CN104354916B (en) * | 2014-10-17 | 2016-08-24 | 昆山宝莱特机械有限公司 | A kind of bipack-film mechanism |
| CN105751452A (en) * | 2016-04-22 | 2016-07-13 | 苏州超群智能科技有限公司 | Mechanical arm with visual image system |
| CN108750652A (en) * | 2018-07-10 | 2018-11-06 | 株洲四点零智能科技有限公司 | A kind of pcb board handling equipment |
| CN109548489A (en) * | 2018-12-27 | 2019-04-02 | 海安智鹏自动化科技有限公司 | A kind of apple picking robot based on yolo vision |
| CN110110760A (en) * | 2019-04-17 | 2019-08-09 | 浙江工业大学 | A kind of workpiece positioning and recognition methods based on machine vision |
| CN109928207B (en) * | 2019-04-24 | 2020-09-15 | 苏州凌云视界智能设备有限责任公司 | Liquid crystal screen carrying device |
| JP7372076B2 (en) * | 2019-08-07 | 2023-10-31 | ファナック株式会社 | image processing system |
| CN112122736A (en) * | 2020-09-25 | 2020-12-25 | 南宁科泰机械设备有限公司 | Automatic welding device for civil air defense door frame |
| CN112456128B (en) * | 2020-12-04 | 2021-11-05 | 深圳市宏申工业智能有限公司 | Automatic loading and unloading method and system on production line based on machine vision |
| CN112348815B (en) * | 2021-01-07 | 2021-04-06 | 新东方教育科技集团有限公司 | Image processing method, image processing apparatus, and non-transitory storage medium |
-
2021
- 2021-09-30 CN CN202111166209.1A patent/CN114056920B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114056920A (en) | 2022-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110534334B (en) | Automatic lamination robot for transformer iron core | |
| CN207451079U (en) | A kind of automatic charging blanking equipment of service plate | |
| CN108237090A (en) | A kind of battery core module automatic fraction collector | |
| CN206705277U (en) | Self-feeding machine people's system integration | |
| CN114056920B (en) | Lamination machine based on machine vision and sheet calibration method and control method thereof | |
| EP1847490A1 (en) | Device and method for automatic palletising and/or depalletising of containers | |
| CN106019041A (en) | Pressing apparatus and touch control panel surface inductor detection apparatus | |
| CN104807832A (en) | Automatic fine inspection production line of silicon ingot | |
| CN111729871B (en) | Color difference detection equipment compatible with various products | |
| CN206327893U (en) | A kind of adjustable conveying robot of attitude | |
| CN209291507U (en) | A kind of AOI automatic deploying and retracting trigger | |
| CN216819897U (en) | Cell-phone center outward appearance detection mechanism | |
| CN111699056A (en) | Automatic loading and unloading device and method of punching machine based on vision and punching equipment | |
| CN208044297U (en) | A kind of dual stage face LDI automatic connectings | |
| CN205346287U (en) | Positioning material receiving device | |
| CN110844599A (en) | Automatic laminating production line of TV set screen backplate | |
| CN110933845A (en) | PCB aluminum sheet unloading mechanism | |
| CN212952904U (en) | Bad plate removing device | |
| CN211481639U (en) | Automatic pre-stacking system for semi-cured core boards | |
| CN211846318U (en) | Intelligent dismounting device | |
| CN211378390U (en) | PCB aluminum sheet unloading mechanism | |
| CN210026631U (en) | Full-automatic sheet silk screen printing machine | |
| CN218872897U (en) | Packaging material quality control system based on machine vision | |
| CN117300399A (en) | Robot gets material dinner plate marking device | |
| CN217971565U (en) | Automatic conveyer that snatchs of commodity circulation carton |
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 |