KR102437009B1 - Computer vision-based welding robot vision device and method thereof - Google Patents

Abstract

The present invention comprises the steps of moving a torch gun to a welding target using a vision sensor; performing welding on a welding object using a torch gun; and performing a welding quality inspection on the welding object using a vision sensor, wherein when performing at least one of welding and the welding quality inspection, spraying air to the welding object , a welding method is disclosed. According to the present invention, the vision sensor is protected from sparks and welding quality inspection can be performed smoothly.

Description

Computer vision-based welding robot vision device and method {COMPUTER VISION-BASED WELDING ROBOT VISION DEVICE AND METHOD THEREOF}

The present invention relates to a computer vision-based welding robot vision apparatus and method, and more particularly, to a method for performing welding based on vision sensing and a welding robot using the same.

Industrial products such as machines and plants rarely consist of only one member, and are made by joining at least two or more members. Main methods for joining two metal members include mechanical bonding using rivets or bolts, chemical bonding using adhesives, etc., and metal bonding such as welding. Among these joints, welding is widely used from the viewpoints of joint strength, efficiency, material and man-hour reduction, etc., and is an essential basic processing technology in almost all industrial fields.

Welding is a method of joining by applying heat, pressure, or heat and pressure to a junction of a base material, that is, a member to be joined, and is divided into fusion welding, pressure welding, and brazing.

As a welding method that is widely used in various industrial fields, there is arc welding in which a base material is melted using arc heat. Arc welding is a type of fusion welding, but it is the most common welding method, and when simply referring to welding, arc welding is often referred to. Arc welding is characterized by high joint efficiency and excellent airtightness because joints can be continuously integrated.

In arc welding, a voltage is applied as a welding power source between the welding wire supplied from the welding torch and the base material, thereby generating an arc between the welding wire and the base material. This arc heat causes welding between the base metal and the base metal while melting the welding wire. Since the welding wire according to arc welding melts and falls, the welding wire is continuously supplied through the welding torch by the feeding device during welding.

Solid welding is achieved by solidifying the weld metal in which the base metal and the welding wire are melted to form a weld bead. In the case of heavy-duty plate welding, it is necessary to secure the welding amount or penetration depth by widening the weld bead width in order to maintain the strength of the welded part. In the case of heavy-duty plate welding, welding strength is secured by widening the bead width by welding by weaving in which the welding torch is interlocked from side to side.

In addition, in the welding torch, an inert gas called a shield gas, for example, carbon dioxide or argon gas is supplied so as to protect the arc column from the atmosphere. In addition, the molten metal after melting is also protected from the atmosphere by the gas generated by decomposition of the flux contained in the welding wire, thereby suppressing welding defects such as blow holes.

As welding methods other than arc welding, there are spot welding and laser welding.

Spot welding is classified as overlap resistance welding, which is a type of piezoelectricity. Electricity flows while pressing two overlapping thin plates from both sides, and the resistance heat melts the two plates and welds them. Laser welding is a welding method using a laser. Because lasers have a high energy density, they can be pinpointed to melt the weld face by tightening the energy. Therefore, deep penetration welding is possible with low heat input and low energy.

After arc welding robots were developed as 6-axis Cartesian robots in Japan in 1975, arc welding robots have exploded in popularity since 1980.

The welding robot is a relatively large size robot, and the current arc welding robot is a 6-axis vertical articulated robot. Since the robot wrist structure includes an axis that rotates in a Roll, Bend, and Roll manner sequentially from the torch, it is called an RBR structure and is the most common wrist structure among industrial robots.

As a related technology, Korean Patent Registration No. 10-0241847 relates to a method and device for controlling a welding robot using a laser vision sensor. In the point of disclosing a technique for driving a welding robot using coordinates, it is distinguished from the present invention, which aims to remove sparks and smog generated during welding, in object, configuration and effect.

As a related art, Korean Patent Registration No. 10-1010788 relates to a welding robot apparatus and a control method thereof, and a correction value of the welding torch is calculated using the current value of both ends of the weaving, and the correction value of the welding torch is used by using the calculated correction value. In the point of disclosing a technique for correcting a position, it is distinguished from the present invention, which aims to eliminate sparks and smog generated during welding, in object, configuration and effect.

However, according to the prior art, since the welding robot is automatically driven, it is necessary to measure the welding position using various sensors. Among these sensors are vision sensors that collect vision data, such as the human eye. However, since the vision sensor has to photograph the welding target, it is generally disposed at a close distance to the torch end where welding occurs. Since the vision sensor is mounted on the torch gun, there is a high risk of damage due to sparks generated during welding.

In addition, since the welding robot continuously performs multiple welding operations, it is necessary to perform a welding quality inspection in the middle. However, due to welding smog during welding, astigmatism may not be performed properly, or noise may be included in the sensing data collected by the vision sensor.

A welding method and a welding robot vision apparatus using the same according to an embodiment of the present invention were invented to solve problems caused by sparks and smog that may occur when the welding robot is driven.

Korean Patent Registration No. 10-0241847 (published on March 02, 2000) Korean Patent Registration No. 10-1010788 (published on Jan. 23, 2011)

One problem to be solved by the present invention is to solve the problems of the welding robot according to the prior art in which a sensor damage due to a spark and a recognition disorder due to smog occurred.

One problem to be solved by the present invention is to provide a welding robot vision device in which a vision sensor can be protected from sparks.

An object of the present invention is to provide a welding robot vision apparatus capable of removing welding smog during welding quality inspection.

A welding method according to an embodiment of the present invention is a method performed by a welding robot, comprising: moving a torch gun to a welding target using a vision sensor; performing welding on a welding object using a torch gun; and performing a weld quality check on the weld target using a vision sensor, wherein when performing at least one of welding and the weld quality check, spraying air on the weld target can be

A welding method according to an embodiment of the present invention is a method performed by a welding robot, comprising: moving a torch gun to a welding target using a vision sensor; performing welding on a welding object using a torch gun; and performing a welding quality inspection on the welding object using a vision sensor, wherein when performing at least one of welding and the welding quality inspection, controlling a compressor to spray air to the welding object ; and controlling an injection direction of the air for selective injection of air to sparks and smog.

A welding method according to an embodiment of the present invention is a method performed by a welding robot, comprising: moving a torch gun to a welding target using a vision sensor; performing welding on a welding object using a torch gun; and performing a welding quality inspection on the welding object using a vision sensor, wherein when performing at least one of welding and the welding quality inspection, controlling a compressor to spray air to the welding object step; and controlling the output of the nozzle to spray air through the first nozzle for sparks and through the second nozzle for smog.

A welding robot vision apparatus according to an embodiment of the present invention includes: a compressor for generating air pressure required for air jetting to a welding target; a vision sensor for generating sensing data about a welding line of a welding target; a data processing unit that converts the sensed data into three-dimensional data; and a processor for controlling the movement of the torch gun based on the three-dimensional data, wherein the processor may be configured to control the compressor for the air injection based on the three-dimensional data.

A welding robot vision apparatus according to an embodiment of the present invention includes: a compressor for generating air pressure required for air jetting to a welding target; a vision sensor for generating sensing data about a welding line of a welding target; a data processing unit that converts the sensed data into three-dimensional data; at least one nozzle that protects the vision sensor from sparks and sprays air to remove smog for welding quality inspection; and a processor for controlling movement of the torch gun based on the three-dimensional data, wherein the processor may be configured to control the nozzle for spraying the air based on the three-dimensional data.

In addition, the air is characterized in that it is injected toward sparks and smog generated by welding.

In addition, the air is characterized in that it is injected toward the spark from the first nozzle disposed around the vision sensor.

In addition, the air is characterized in that it is injected toward the spark through the inside of the vision sensor.

In addition, the air is sprayed through the inside of the vision sensor to cool the vision sensor.

In addition, the welding robot vision apparatus further includes a spark detection unit that detects a spark generated during welding by using the sensing data, and the processor is configured to: a direction of the nozzle and the welding torch to prevent sparks from flowing into the vision sensor may be configured to control at least one of the movements of

In addition, the welding robot vision apparatus further includes a smog detection unit for detecting smog generated during welding using sensing data, and the processor includes: a direction of the nozzle and the welding torch to remove smog during welding quality inspection may be configured to control at least one of the movements of

Specific details of other embodiments are included in "Details for carrying out the invention" and attached "drawings".

Advantages and/or features of the present invention, and methods for achieving them, will become apparent with reference to various embodiments described below in detail in conjunction with the accompanying drawings.

However, the present invention is not limited to the configuration of each embodiment disclosed below, but may also be implemented in a variety of different forms, and each embodiment disclosed herein only makes the disclosure of the present invention complete, It is provided to fully inform those of ordinary skill in the art to which the scope of the present invention belongs, and it should be understood that the present invention is only defined by the scope of each of the claims.

According to the present invention, the vision sensor can be protected from sparks generated during welding.

In addition, it is possible to collect noise-free sensing data through the vision sensor while smog generated by welding is removed.

In addition, the efficiency of robot welding operation is increased by removing welding sparks and smog.

1 is a schematic illustration of a welding robot according to an embodiment of the present invention.
2 is an exemplary view of a torch gun including a vision sensor.
3 is an exemplary view of a torch gun according to an embodiment of the present invention.
4 is a block diagram of a welding robot vision apparatus according to an embodiment of the present invention.
5 is a flowchart of a welding method according to an embodiment of the present invention.

Before describing the present invention in detail, the terms or words used herein should not be construed as being unconditionally limited to their ordinary or dictionary meanings, and in order for the inventor of the present invention to describe his invention in the best way It should be understood that the concepts of various terms can be appropriately defined and used, and further, these terms or words should be interpreted as meanings and concepts consistent with the technical idea of the present invention.

That is, the terms used in this specification are only used to describe preferred embodiments of the present invention, and are not used for the purpose of specifically limiting the content of the present invention, and these terms represent various possibilities of the present invention. It should be noted that the term has been defined with consideration in mind.

Also, in this specification, it should be understood that, unless the context clearly indicates otherwise, the expression in the singular may include a plurality of expressions, and even if it is similarly expressed in plural, it should be understood that the meaning of the singular may be included. .

In the case where it is stated throughout this specification that a component "includes" another component, it does not exclude any other component, but further includes any other component unless otherwise indicated. It could mean that you can.

Furthermore, when it is described that a component is "exists in or is connected to" of another component, this component may be directly connected or installed in contact with another component, and a certain It may be installed spaced apart by a distance, and in the case of being installed spaced apart by a certain distance, a third component or means for fixing or connecting the corresponding component to another component may exist, and now It should be noted that the description of the components or means of 3 may be omitted.

On the other hand, when it is described that a certain element is "directly connected" or "directly connected" to another element, it should be understood that the third element or means does not exist.

Likewise, other expressions describing the relationship between components, such as "between" and "immediately between", or "adjacent to" and "directly adjacent to", have the same meaning. should be interpreted as

In addition, if terms such as "one side", "other side", "one side", "other side", "first", "second" are used in this specification, with respect to one component, this one component is It is used to be clearly distinguished from other components, and it should be understood that the meaning of the component is not limitedly used by such terms.

In addition, in this specification, terms related to positions such as "upper", "lower", "left", "right", etc., if used, should be understood as indicating a relative position in the drawing with respect to the corresponding component, Unless an absolute position is specified for their position, these position-related terms should not be construed as referring to an absolute position.

In addition, in this specification, in specifying the reference numerals for each component of each drawing, the same component has the same reference number even if the component is indicated in different drawings, that is, the same reference is made throughout the specification. The symbols indicate the same components.

In the drawings attached to this specification, the size, position, coupling relationship, etc. of each component constituting the present invention are partially exaggerated, reduced, or omitted for convenience of explanation or in order to sufficiently clearly convey the spirit of the present invention. may be described, and thus the proportion or scale may not be exact.

In addition, in the following, in describing the present invention, a detailed description of a configuration determined that may unnecessarily obscure the subject matter of the present invention, for example, a detailed description of a known technology including the prior art may be omitted.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the related drawings.

1 is a schematic illustration of a welding robot according to an embodiment of the present invention.

Referring to FIG. 1 , the welding robot 10 is configured to include a torch gun 100 , a wire feed 210 , an arm driving unit 220 , a control unit 300 , a power source 400 and a compressor 500 . can be

The torch gun 100 may be configured to include a torch and a vision sensor. The torch attached to one end of the torch gun 100 melts the wire with heat and pressure to perform welding on the welding object, that is, the base material.

The wire feed 210 smoothly supplies the welding wire to the torch while releasing the welding wire in the wound state.

The arm driving unit 220 moves the positions of the torch and the torch gun 100 through hydraulic equipment or motor control.

The controller 300 may control the operation of all components constituting the welding robot 10 . For example, the controller 300 may detect the location and amount of sparks and smog, and control the compressor and the nozzle according to the detection result to spray air.

The power source 400 functions to supply voltage and current required for welding.

The compressor 500 serves to generate an air pressure required for air injection to remove sparks and smog.

2 is an exemplary view of a torch gun including a vision sensor.

Referring to FIG. 2 , a welding robot that performs welding using vision recognition may be configured to include a vision sensor 110 as a component of the torch gun 100 in addition to the torch 120 . The vision sensor 110 may be configured to include an RGB sensor, a laser sensor, and a device for adjusting the direction of the sensor according to the type.

3 is an exemplary view of a torch gun according to an embodiment of the present invention.

Referring to FIG. 3 , a side view of the torch gun 100 of the welding robot 10 according to an embodiment of the present invention is depicted.

The torch gun 100 may be configured to include a vision sensor 110 , a torch 120 , and nozzles 131 and 132 .

The vision sensor 110 functions to collect sensing data so that the welding robot 10 can perform welding based on vision recognition. The collected sensing data is output as a three-dimensional coordinate value through data processing, and the welding robot 10 performs welding while moving a torch along a welding line using the three-dimensional coordinate value. The vision sensor 110 may be configured to include a laser, a lens, and a semiconductor chip such as an image processor.

Torch 120 may be configured internally to include a torch stage, a torch brake, and an insulating disk. The torch stage functions to perform welding using an applied voltage and wire. The torch brake may perform a function of separating the torch end from the torch gun when a problem such as a collision occurs at the torch end. The insulating disk functions to prevent current from flowing from the torch gun to the device below the arm driving part of the welding robot due to a short circuit or the like.

The nozzle 130 functions to spray air using the air pressure generated by the compressor 500 . The nozzle 130 may be configured to include at least one or more nozzles, for example, one first nozzle 131 or two first nozzles 131 and second nozzles 132 .

The first nozzle 131 is preferably disposed adjacent to the vision sensor 110 . For example, referring to FIG. 2 , the first nozzle 131 may be disposed around the vision sensor 100 or inside the vision sensor 100 . Referring to FIG. 3 , the side of the vision sensor 100 is depicted, and air may be injected through the nozzle 131 at the position of the vision sensor 100 . The semiconductor chip of the vision sensor 100 that may generate high heat due to air injection may be cooled.

When one first nozzle 131 is installed in the welding robot 10 , the direction of the nozzle is controlled by the controller 300 so that the first nozzle 131 can form a first air direction and a second air direction as shown in FIG. 3 . ) can be controlled by Here, in the first air direction, the welding robot 10 may remove the spark toward the vision sensor 100 through air injection. In the second air direction, the welding robot 10 may remove welding smog during welding quality inspection through air injection.

Referring back to FIG. 3 , a second nozzle 131 that is additionally disposed after the first nozzle may be disposed at the torch end. The second nozzle may remove smog generated from the welding target after welding at the position of the torch end through air injection.

4 is a block diagram of a welding robot vision apparatus according to an embodiment of the present invention.

Referring to FIG. 4 , the controller 300 may be configured to include a processor 310 , an interface 320 , a data processor 330 , a spark detector 340 , and a smog detector 350 .

The processor 310 may control driving of the welding robot according to a control algorithm of the welding robot. Here, the driving control of the welding robot includes control of the vision sensor 110 , the torch 120 , the nozzle 130 , the wire feeder 210 , the arm driving unit 220 , the power source 400 , and the compressor 500 . include

The interface 320 refers to a user interface that connects a user and the welding robot. The interface 320 includes an input interface and an output interface, and the input interface may be implemented as a keyboard and a touch screen, and the output interface may be implemented as a display, a vibration module, and a speaker.

The data processing unit 330 functions to process the sensed data received from the vision sensor 110 . The data processing unit 330 may perform pre-processing such as various corrections of the sensed data and post-processing of extracting 3D coordinate values.

The wire feeder 210 performs a function of allowing the wire used for welding to be smoothly supplied to the torch.

The arm driving unit 220 functions to control the movement of the entire arm constituting the welding robot 10 , that is, the roll value of the joint, that is, rotation.

The power source 400 functions to generate voltage and current used for welding.

The compressor 500 functions to generate air used for spark and smog removal through air pressure.

The welding robot 10 according to an embodiment of the present invention is characterized in that it detects sparks and smog generated during welding by using the vision sensor 110 . Sparks may be removed to protect the vision sensor 110 , and smog may be removed to efficiently conduct weld quality inspections.

The spark detection unit 340 may detect the amount of sparks generated during welding and the location of the sparks. The spark detection unit 340 may detect the spark through various methods. For example, the position and amount of the spark may be detected by comparing the received sensing data with a pre-stored image library related to the spark.

Also, the spark detector 340 may detect the location and amount of the spark using an artificial neural network learned through training, for example, a convolutional neural network.

The smog detector 350 may detect the amount of smog generated during welding and the location of the spark. The smog detector 340 may detect smog through various methods. For example, the position and amount of smog may be detected by comparing received sensing data with a pre-stored image library on smog.

Also, the smog detector 350 may detect the location and amount of smog using an artificial neural network learned through training, for example, a convolutional neural network.

The processor 310 may control the injection position and amount of air through nozzle control according to the detected location and amount of spark and smog.

5 is a flowchart of a welding method according to an embodiment of the present invention.

Referring to FIG. 5 , in the welding method (S100) according to an embodiment of the present invention, moving a welding torch to a welding target using a vision sensor (S100), and performing welding on a welding target using the welding torch (S100) It may be configured to include a step (S120) of performing a welding quality inspection on a welding target using a vision sensor (S130). A welding method according to an embodiment of the present invention will be described with reference to FIGS. 1, 3 and 4 .

In step S110 , the welding robot 10 may move a torch gun to a welding target using a vision sensor. The welding robot 10 may collect sensing data using the vision sensor 110 . The sensing data collected by the vision sensor 110 is transmitted to the control unit 300 , and the processor 310 of the control unit 300 may derive a 3D coordinate value from the sensed data using the data processing unit 320 . . The welding robot 10 may position the torch 120 on the welding target through the control of the arm driving unit 220 using the derived three-dimensional coordinate values. The arm driving unit 220 may control the position of the torch 120 by rotationally driving the frustration part where the corresponding arm is replaced using hydraulic pressure or a motor.

In step S120 , the welding robot 10 may perform welding on a welding target using the torch 120 . The torch 120 end is provided with a wire according to the welding method, for example, in the case of arc welding. As the wire is melted by the voltage applied between the base material and the wire to be welded, arc welding can be performed between the base material. An arc, that is, a spark, is generated during a welding operation. In addition, the generated spark may be directed in an omni-directional direction, and in particular, the spark bouncing toward the vision sensor 110 may damage the cover, lens and components of the vision sensor 110 , for example, a PCB.

The welding robot 10 may spray air to the welding target during welding. The target to which the air is sprayed is a target to be welded, particularly a spark generated from the target to be welded.

In order to spray air toward the spark, the amount and position of the spark are sensed by the spark detection unit 340, and based on the detection result, the welding robot 10 controls the nozzle 130 and the compressor 500 to control the air. You can adjust the amount and position.

The welding robot 10 may perform a welding quality inspection using a vision sensor. The welding quality of the welding target may be inspected by comparing the image library of the pre-stored welding result with the sensing data of the vision sensor after welding. Since vision inspection of weld quality is a very sophisticated task, noise-free sensing data must be collected. However, it may be difficult to proceed with the welding inspection due to smog generated after welding.

In step S130 , the welding robot 10 may perform a welding quality inspection on a welding target using a vision sensor. The welding robot 10 may sequentially repeat multiple welding operations. When a welding operation is completed on one welding object, a quality check for the welding operation is performed. And the welding target that does not pass the quality inspection is checked for quality problems, and the welding target is sequentially moved through the conveyor belt system.

When inspecting the quality of the welding object, the welding robot 10 analyzes the position and amount of smog detected by the smog detection unit 350 , and controls the nozzle 130 and the compressor 500 based on the analysis data Smog can be removed by blowing air through the

As described above, according to an embodiment of the present invention, the vision sensor may be protected from sparks generated during welding.

In addition, it is possible to collect noise-free sensing data through the vision sensor while smog generated by welding is removed.

In addition, the efficiency of robot welding operation is increased by removing welding sparks and smog.

In the above, although several preferred embodiments of the present invention have been described with some examples, the descriptions of various various embodiments described in the "Specific Contents for Carrying Out the Invention" item are merely exemplary, and the present invention Those of ordinary skill in the art will understand well that the present invention can be practiced with various modifications or equivalents to the present invention from the above description.

In addition, since the present invention can be implemented in various other forms, the present invention is not limited by the above description, and the above description is intended to complete the disclosure of the present invention, and is generally It should be understood that this is only provided to fully inform those with knowledge of the scope of the present invention, and that the present invention is only defined by each of the claims.

10: welding robot
100: torch gun
110: vision sensor
120: torch
210: wire feeder
220: arm drive unit
300: control unit
310: processor
320: interface
330: data processing unit
340: spark detection unit
350: smog detection unit
400: power source
500: compressor

Claims (5)

A method performed by a welding robot, comprising:
moving a torch gun to a welding target using a vision sensor;
performing welding on a welding object using the torch gun; and
performing a weld quality inspection on the weld target using the vision sensor,
By spraying air through a first nozzle disposed around the vision sensor or inside the vision sensor to remove a spark toward the vision sensor, and spraying air through a second nozzle disposed at the torch end of the torch gun, To remove smog generated from the welding target after welding,
welding method.
A method performed by a welding robot, comprising:
moving a torch gun to a welding target using a vision sensor;
performing welding on a welding object using the torch gun;
performing a welding quality inspection on the welding object using the vision sensor; and
Including; when performing at least one of the welding and the welding quality inspection, controlling a compressor to spray air to the welding target;
By spraying air through a first nozzle disposed around the vision sensor or inside the vision sensor to remove a spark toward the vision sensor, and spraying air through a second nozzle disposed at the torch end of the torch gun, To remove smog generated from the welding target after welding,
welding method.
A method performed by a welding robot, comprising:
moving a torch gun to a welding target using a vision sensor;
performing welding on a welding object using the torch gun;
performing a welding quality inspection on the welding object using the vision sensor;
when performing at least one of the welding and the welding quality inspection, controlling a compressor to spray air to the welding target; and
The first nozzle and the second nozzle for spraying air through a first nozzle disposed in the vicinity of the vision sensor or inside the vision sensor for sparks, and through a second nozzle disposed at the torch end of the torch gun for smog 2 configured to include controlling the output of the nozzle,
welding method.
a compressor for generating air pressure required for air jetting to the welding target;
a vision sensor for generating sensing data on a welding line of the welding target;
a data processing unit converting the sensed data into 3D data; and
A processor for controlling the movement of the torch gun based on the three-dimensional data,
The processor is
configured to control the compressor for the air injection based on the three-dimensional data,
A first nozzle is disposed around the vision sensor or inside the vision sensor, and a second nozzle is disposed at a torch end of the torch gun,
spraying air through the first nozzle to remove sparks directed toward the vision sensor, and spraying air through the second nozzle to remove smog generated from the welding target after welding;
Welding robot vision device.
a compressor for generating air pressure required for air jetting to the welding target;
a vision sensor for generating sensing data on a welding line of the welding target;
a data processing unit converting the sensed data into 3D data;
a first nozzle disposed around the vision sensor or inside the vision sensor to spray air to remove sparks directed toward the vision sensor;
a second nozzle disposed at the torch end to spray air to remove smog generated from the welding target after welding; and
A processor for controlling the movement of the torch gun based on the three-dimensional data,
The processor is
configured to control the first nozzle and the second nozzle for the air jet based on the three-dimensional data,
Welding robot vision device.

Images