CN110732814A - intelligent welding robot based on vision technology - Google Patents
intelligent welding robot based on vision technology Download PDFInfo
- Publication number
- CN110732814A CN110732814A CN201910933131.8A CN201910933131A CN110732814A CN 110732814 A CN110732814 A CN 110732814A CN 201910933131 A CN201910933131 A CN 201910933131A CN 110732814 A CN110732814 A CN 110732814A
- Authority
- CN
- China
- Prior art keywords
- sensor
- welding
- end effector
- vision
- central control
- 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.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K37/00—Auxiliary devices or processes, not specially adapted to a procedure covered by only one of the preceding main groups
- B23K37/02—Carriages for supporting the welding or cutting element
- B23K37/0252—Steering means
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Robotics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Optics & Photonics (AREA)
- Manipulator (AREA)
Abstract
The invention discloses intelligent welding robots based on a vision technology, which comprises an end effector, a vision sensor, six-axis mechanical arms, a central control panel and a neural network computing unit, wherein the end effector is connected to end joints of the six-axis mechanical arms, the vision sensor is fixed on the end effector, the vision sensor moves along with the end effector, the neural network computing unit is arranged on the central control panel, and the end effector, the vision sensor and the six-axis mechanical arms are respectively and electrically connected to the central control panel.
Description
Technical Field
The invention relates to the field of intelligent processing equipment, in particular to intelligent welding robots based on a vision technology.
Background
For automatic welding equipment, different welding objects are often faced, welding paths or welding points are required to be manually set when a new object is welded at each time, the automatic welding equipment is processed according to a set mode, the situation that the welding position is changed greatly cannot be adapted, manual intervention is required at the time, and the automatic welding equipment cannot adapt to a new welding environment quickly, so that the operation requirement on workers is high, the labor cost is occupied, and the automatic welding equipment is not convenient enough.
Disclosure of Invention
In order to solve the above problems, the present invention provides intelligent welding robots based on visual technology, which can automatically learn the characteristics of the welding object by using a neural network computing unit, and can directly identify the learned object in a new environment, thereby reducing the trouble of human intervention.
The technical scheme adopted by the invention for solving the problems is as follows:
A smart welding robot based on vision technology, comprising:
the end effector is used for contacting a target object to weld;
the vision sensor is used for identifying the welding position of the target object through the image;
a six-axis robotic arm for moving the end effector to a specified position;
the central control panel is used for receiving control instructions and system settings;
the neural network computing unit is used for autonomously learning the welding image transmitted back by the vision sensor so as to quickly identify a new welding environment;
the end effector is connected to the end joint of the six-axis mechanical arm, the visual sensor is fixed on the end effector and moves along with the end effector, the neural network computing unit is arranged on the central control board, and the end effector, the visual sensor and the six-axis mechanical arm are respectively and electrically connected to the central control board.
, the robot further comprises a control panel and a manual rocker for manually controlling the six-axis robot arm, wherein the control panel and the manual rocker are independently arranged beside the six-axis robot arm and are connected to the central control panel through cables.
, the central control panel comprises:
the point positioning module is used for periodically acquiring coordinate points of the six-axis mechanical arm and drawing the coordinate points into a motion path, wherein the coordinate points are related to the deflection position of the motor of each joint point in the six-axis mechanical arm;
a storage module to store the path of motion of the end effector and the image of the vision sensor.
, the end effector is a welding gun, the head of the welding gun is linear, the visual sensor and the head of the welding gun are in the same line , and the orientation of the visual sensor is the same as that of the head of the welding gun.
And , the vision sensor includes a CMOS image sensor and a laser ranging sensor, the CMOS image sensor sends the image of the welding environment to the neural network computing unit, the laser ranging sensor sends the distance information to the neural network computing unit, and the orientation of the CMOS image sensor and the orientation of the laser ranging sensor are the same.
The or more technical schemes provided by the embodiment of the invention have the beneficial effects that the neural network computing unit identifies the image of the welding object obtained by the visual sensor, automatically extracts the characteristic value to obtain the common characteristic of the welding object, automatically completes the welding point identification when a new welding object needs to be welded, displays the welding point to a worker for confirmation and adjustment, and can also adjust the position of the end effector in real time according to the characteristic value in the welding process, thereby reducing the operation of manual intervention and reducing the labor cost.
Drawings
The invention is further illustrated in the following description with reference to the figures and examples.
FIG. 1 is a schematic diagram of a module connection according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the structural connections of an embodiment of the present invention;
FIG. 3 is a schematic view of a vision sensor configuration according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a CPU board structure according to an embodiment of the present invention.
Detailed Description
For purposes of making the objects, aspects and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and examples, it is to be understood that the specific examples are for purposes of illustration only and are not to be construed as limiting the invention.
Referring to fig. 1 and 2, embodiments of the present invention provide intelligent welding robots based on vision techniques, comprising:
an end effector 100 for contacting a target object to perform welding;
a vision sensor 200 for recognizing a welding position of a target object through an image;
a six-axis robot arm 300 for moving the end effector 100 to a specified position;
the central control panel is used for receiving control instructions and system settings;
a neural network computing unit for autonomously learning the welding image transmitted back by the vision sensor 200, thereby rapidly identifying a new welding environment;
the end effector 100 is connected to the end joints of the six-axis robot 300, the visual sensor 200 is fixed on the end effector 100, the visual sensor 200 moves along with the end effector 100, the neural network computing unit is arranged on the central control board, and the end effector 100, the visual sensor 200 and the six-axis robot 300 are respectively and electrically connected to the central control board.
The neural network computing unit is adopted to identify the image sent by the vision sensor 200, characteristic values can be extracted from the positions of the welding points and the shapes and sizes of the welding lines, training is completed through a neural network algorithm, and when the end effector 100 moves to a new welding environment, the neural network computing unit can rapidly identify the new welding environment by comparing the characteristic values, so that automatic welding is realized, and manual intervention is reduced.
Preferably, the six-axis robot arm further comprises a control panel 400 and a manual rocker 500 for manually controlling the six-axis robot arm 300, wherein the control panel 400 and the manual rocker 500 are independently arranged beside the six-axis robot arm 300 and are connected to the central control panel through cables. The control panel 400 includes, but is not limited to, start/stop buttons, a display screen, an operation status indicator lamp, and an input device according to general settings, and in addition, the manual rocker 500 is linked with the six-axis robot arm 300, and a worker can operate the manual rocker 500 to adjust the pose of the six-axis robot arm 300, and in the process, the central control board collects and stores the movement path, and reproduces the welding path adjusted by the worker during batch processing.
Referring to fig. 4, preferably, the central control board includes:
a point positioning module for periodically acquiring coordinate points of the six-axis robot arm 300 and drawing the coordinate points into a motion path, wherein the coordinate points are related to the deflection positions of the motors of the joint points in the six-axis robot arm 300;
a storage module for storing the motion path of the end effector 100 and the image of the vision sensor 200.
Based on the function of recording the movement path, the movement path can be acquired, besides the manual adjustment and positioning mode of a worker, the manual adjustment and positioning mode can also be a mode that the worker inputs a target position in a programming mode, the central control board tries to run the six-axis mechanical arm 300 to the target position, and the central control board is converted into the movement path according to the deflection position of the motor of each joint point in the six-axis mechanical arm 300 after fine adjustment; the final movement path is stored in a memory module for direct recall during the final machining.
Referring to fig. 3, the vision sensor 200 includes a CMOS image sensor 210 and a laser ranging sensor 220, the CMOS image sensor 210 transmits an image of a welding environment to a neural network computing unit, the laser ranging sensor 220 transmits distance information to the neural network computing unit, and the CMOS image sensor 210 and the laser ranging sensor 220 are oriented in the same direction, the welding positioning is facilitated by using the conventional welding torch 110 as the end effector 100, and actually, different end effectors 100 can be replaced according to different welding objects, but generally, the end effector 100 is oriented to a welding object, and the vision sensor 200 is oriented in the same direction as the end effector 100 to facilitate image and distance acquisition, and in the embodiment, 3D mapping in space is achieved by using two sensors, namely, the CMOS image sensor 210 and the laser ranging sensor 220, and the adaptability to complex welding objects is determined by .
In the embodiment of the invention, the neural network computing unit identifies the image of the welding object obtained by the visual sensor 200, automatically extracts the characteristic value to obtain the common characteristic of the welding object, automatically completes the identification of the welding point when a new welding object needs to be welded, displays the welding point for the confirmation and adjustment of a worker, and can also adjust the position of the end effector 100 in real time according to the characteristic value in the welding process, thereby reducing the operation of manual intervention and reducing the labor cost.
The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and the present invention shall fall within the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means.
Claims (5)
1, intelligent welding robot based on vision technique, which is characterized in that the robot comprises
An end effector (100) for contacting a target object to weld;
a vision sensor (200) for recognizing a welding position of a target object through an image;
a six-axis robotic arm (300) for moving the end effector (100) to a specified position;
the central control panel is used for receiving control instructions and system settings;
a neural network computing unit for autonomously learning the welding image transmitted back by the vision sensor (200) so as to quickly identify a new welding environment;
the end effector (100) is connected to an end joint of the six-axis mechanical arm (300), the visual sensor (200) is fixed on the end effector (100), the visual sensor (200) moves along with the end effector (100), the neural network computing unit is arranged on the central control board, and the end effector (100), the visual sensor (200) and the six-axis mechanical arm (300) are respectively and electrically connected to the central control board.
2. Intelligent welding robot based on vision technique, as claimed in claim 1, further comprising a control panel (400) and a manual rocker (500) for manually controlling the six-axis robot arm (300), the control panel (400) and manual rocker (500) being independently disposed beside the six-axis robot arm (300) and connected to the central control board by cables.
3. Intelligent welding robot based on vision technique, as claimed in claim 1, wherein the central control board comprises:
a point positioning module for periodically acquiring coordinate points of the six-axis robot arm (300) and drawing the coordinate points into a motion path, the coordinate points being related to deflection positions of motors of respective joint points in the six-axis robot arm (300);
a storage module for storing the path of motion of the end effector (100) and the image of the vision sensor (200).
4. Intelligent welding robot based on vision technique as claimed in claim 1, wherein the end effector (100) is a welding torch (110), the head of the welding torch (110) is linear, the vision sensor (200) is in the same line as the head of the welding torch (110), and the orientation of the vision sensor (200) is the same as the orientation of the head of the welding torch (110).
5. Intelligent welding robot based on vision technique, according to claim 4, characterized in that the vision sensor (200) includes a CMOS image sensor (210) and a laser ranging sensor (220), the CMOS image sensor (210) sends the image of the welding environment to the neural network computing unit, the laser ranging sensor (220) sends the distance information to the neural network computing unit, the orientation of the CMOS image sensor (210) and the laser ranging sensor (220) is the same.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910933131.8A CN110732814A (en) | 2019-09-29 | 2019-09-29 | intelligent welding robot based on vision technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910933131.8A CN110732814A (en) | 2019-09-29 | 2019-09-29 | intelligent welding robot based on vision technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110732814A true CN110732814A (en) | 2020-01-31 |
Family
ID=69269752
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910933131.8A Pending CN110732814A (en) | 2019-09-29 | 2019-09-29 | intelligent welding robot based on vision technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110732814A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112404658A (en) * | 2020-10-19 | 2021-02-26 | 中国石油天然气集团有限公司 | Remote control-based in-service pipeline arc 3D printing repair system and method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106874914A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | A kind of industrial machinery arm visual spatial attention method based on depth convolutional neural networks |
| CN206632567U (en) * | 2017-04-11 | 2017-11-14 | 池州职业技术学院 | A kind of Intelligent welding robot device based on machine vision |
| CN107999955A (en) * | 2017-12-29 | 2018-05-08 | 华南理工大学 | A kind of six-shaft industrial robot line laser automatic tracking system and an automatic tracking method |
| CN108406091A (en) * | 2017-02-09 | 2018-08-17 | 发那科株式会社 | Laser Machining head and the laser-processing system for having filming apparatus |
| CN108544153A (en) * | 2018-04-23 | 2018-09-18 | 哈尔滨阿尔特机器人技术有限公司 | A kind of vision robot's system for Tube-sheet Welding |
| CN109175608A (en) * | 2018-09-30 | 2019-01-11 | 华南理工大学 | Weld bead feature points position On-line Measuring Method and seam track automatic measurement system |
| CN110039158A (en) * | 2019-05-15 | 2019-07-23 | 上海应用技术大学 | A kind of welder and welding procedure of flat wire armature |
| CN110135513A (en) * | 2019-05-22 | 2019-08-16 | 广东工业大学 | A kind of weld joint recognition method of the welding robot based on deep learning |
-
2019
- 2019-09-29 CN CN201910933131.8A patent/CN110732814A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106874914A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | A kind of industrial machinery arm visual spatial attention method based on depth convolutional neural networks |
| CN108406091A (en) * | 2017-02-09 | 2018-08-17 | 发那科株式会社 | Laser Machining head and the laser-processing system for having filming apparatus |
| CN206632567U (en) * | 2017-04-11 | 2017-11-14 | 池州职业技术学院 | A kind of Intelligent welding robot device based on machine vision |
| CN107999955A (en) * | 2017-12-29 | 2018-05-08 | 华南理工大学 | A kind of six-shaft industrial robot line laser automatic tracking system and an automatic tracking method |
| CN108544153A (en) * | 2018-04-23 | 2018-09-18 | 哈尔滨阿尔特机器人技术有限公司 | A kind of vision robot's system for Tube-sheet Welding |
| CN109175608A (en) * | 2018-09-30 | 2019-01-11 | 华南理工大学 | Weld bead feature points position On-line Measuring Method and seam track automatic measurement system |
| CN110039158A (en) * | 2019-05-15 | 2019-07-23 | 上海应用技术大学 | A kind of welder and welding procedure of flat wire armature |
| CN110135513A (en) * | 2019-05-22 | 2019-08-16 | 广东工业大学 | A kind of weld joint recognition method of the welding robot based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 张明文: "《工业机器人原理及应用 （DELTA并联机器人）》", 30 April 2018, 哈尔滨工业大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112404658A (en) * | 2020-10-19 | 2021-02-26 | 中国石油天然气集团有限公司 | Remote control-based in-service pipeline arc 3D printing repair system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10905508B2 (en) | Remote control robot system | |
| CN111823223B (en) | Robot arm grabbing control system and method based on intelligent stereoscopic vision | |
| CN110170995B (en) | Robot rapid teaching method based on stereoscopic vision | |
| CN106853639A (en) | A kind of battery of mobile phone automatic assembly system and its control method | |
| CN106584093A (en) | Self-assembly system and method for industrial robots | |
| US20090234502A1 (en) | Apparatus for determining pickup pose of robot arm with camera | |
| WO2018043525A1 (en) | Robot system, robot system control device, and robot system control method | |
| KR102403716B1 (en) | robot system | |
| CN113954085A (en) | Intelligent positioning and control method of welding robot based on binocular vision and linear laser sensing data fusion | |
| CN111421528A (en) | Industrial robot's automated control system | |
| CN110170996B (en) | Robot rapid teaching system based on stereoscopic vision | |
| US10175683B2 (en) | Teaching data preparation device and teaching data preparation method for articulated robot | |
| CN111975200A (en) | Intelligent welding method and intelligent welding system based on visual teaching technology | |
| CN113333998A (en) | Automatic welding system and method based on cooperative robot | |
| CN110732814A (en) | intelligent welding robot based on vision technology | |
| US20230286143A1 (en) | Robot control in working space | |
| CN110605720A (en) | Industrial robot vision system and teaching method thereof | |
| WO2020032263A1 (en) | Robot system | |
| CN107363831B (en) | Teleoperation robot control system and method based on vision | |
| JP7190552B1 (en) | Robot teaching system | |
| CN111899629B (en) | Flexible robot teaching system and method | |
| JP6832408B1 (en) | Production system | |
| CN111015675A (en) | Typical robot vision teaching system | |
| CN205571674U (en) | Soldering joint tracking vision sensory control system based on structured light | |
| Yong | RESEARCH ON PATH RECOGNITION OF WELDING MANIPULATOR BASED ON AUTOMATIC CONTROL ALGORITHM. |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200131 |