KR102621008B1 - welding training simulation device using artificial intelligence analysis technology - Google Patents

Abstract

The welding training simulation device using artificial intelligence analysis technology according to the present invention includes a virtual welding mask, a virtual welding base material; virtual welding gun; It includes a simulation control device and a display device, wherein the virtual welding gun includes a virtual welding rod coupled to an end; It includes a sensing unit that detects the distance between the virtual welding rod and the virtual welding base material and the movement path of the virtual welding gun. The simulation control device applies big data deep learning analysis results to the actual welding flame and bead formation images according to the distance between the actual welding rod and the actual welding base material in the actual welding device and the movement path of the actual welding gun, and performs a training process. A virtual welding spark and bead formation image can be generated according to the distance between the virtual welding electrode and the virtual welding base material and the movement path of the virtual welding gun.

Description

Welding training simulation device using artificial intelligence analysis technology}

The present invention relates to a welding training simulation device, and more specifically, to a welding training simulation device that can provide a training environment similar to actual welding using artificial intelligence big data deep learning analysis results.

Arc welding can be said to be a process of joining the joints of metals to be joined through arc discharge. It is done by melting the metal welding rod and welding base material with arc heat and then cooling them.

Since such welding work is generally performed in poor working environments, as welding technology and robot technology develop, the development of various welding work automation technologies is in progress, and many automatic welding devices are already being applied in the field. However, there are still many places that require manual welding, which requires workers to do the welding themselves, depending on the work environment.

This kind of manual welding often requires high precision and safety, and workers also require advanced welding skills and a lot of experience. However, in the current labor market, where people avoid poor working environments and hard physical labor, it is not easy to secure such skilled technicians.

Even if new manpower is secured, it is necessary to undergo a lot of welding training to acquire skilled welding skills. However, in reality, welding training is often carried out by the trainee without specific and objective data on the welding work, and the trainer must use a visual fixture to judge the goodness of the welding condition. As the number of repetitions of welding training increases, the number of welding training required during training increases. Since the consumption of materials also increases significantly, the problem of high costs also arises.

Accordingly, the technical problem that the present invention aims to solve is that it is possible to confirm specific and objective data about the welding training performed by the trainer, it is possible to conduct welding training in an environment similar to actual welding, and it is possible to do so without consuming welding materials. It provides a welding training simulation device using artificial intelligence analysis technology that enables welding training.

The technical problems to be achieved by the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by those skilled in the art from the description below. There will be.

A welding training simulation device using artificial intelligence analysis technology according to the present invention to solve the above technical problem includes a virtual welding mask, a virtual welding base material; virtual welding gun; It may include a simulation control device and a display device.

The virtual welding gun includes a virtual welding rod coupled to an end; It may include a sensing unit that detects the distance between the virtual welding rod and the virtual welding base material and the movement path of the virtual welding gun.

The simulation control device applies big data deep learning analysis results to the actual welding flame and bead formation images according to the distance between the actual welding rod and the actual welding base material in the actual welding device and the movement path of the actual welding gun, and performs a training process. A virtual welding spark and bead formation image can be generated according to the distance between the virtual welding electrode and the virtual welding base material and the movement path of the virtual welding gun.

The simulation control device provides artificial intelligence big data deep learning analysis results for a cyclogram representing the current-voltage relationship during arc welding in the actual welding device according to the distance between the actual welding electrode and the actual welding base material. By applying it, a virtual cyclogram can be generated according to the distance between the virtual welding electrode and the virtual welding base material during the training process, and the trainee's welding work proficiency can be evaluated based on the virtual cyclogram.

The virtual welding gun may further include a virtual welding rod length adjuster capable of advancing or retracting the virtual welding rod. At this time, the simulation control device applies artificial intelligence big data deep learning analysis results to the distance between the actual welding electrode and the actual welding base material and the reduction length of the actual welding electrode according to the actual welding time, and Calculate the virtual reduced length of the virtual welding electrode according to the distance and welding time between the welding electrode and the virtual welding base material, and based on the virtual reduced length, the virtual welding electrode length adjuster so that the virtual welding electrode moves backward into the virtual welding gun. You can control it.

The simulation control device applies artificial intelligence big data deep learning analysis results to the actual mask perspective image in which the actual welding flame and bead formation image is viewed through the actual welding mask, and provides information on the virtual welding flame and bead formation image. A virtual mask perspective image can be created.

The virtual welding mask is connected to the simulation control device through wireless communication and may include a display unit corresponding to a viewing window of the actual welding mask. At this time, the simulation control device may selectively provide the virtual welding flame bead formation image or the virtual mask perspective image through the display unit.

The virtual welding gun may further include an attractive force control unit capable of controlling the attractive force between the virtual welding base material and the virtual welding electrode through current control of the electromagnet. At this time, the simulation control device applies the results of artificial intelligence deep learning analysis of the attractive force between the actual welding electrode and the actual welding base material according to the distance between the actual welding electrode and the actual welding base material, and The virtual force of attraction between the virtual welding electrode and the virtual welding material may be calculated according to the distance between the welding electrode and the virtual welding material, and the force control unit may be controlled to generate a force corresponding to the virtual force.

The virtual welding mask is connected to the simulation control device through wireless communication and may include a speaker. At this time, the simulation control device applies artificial intelligence big data analysis results to the actual welding sound according to the distance between the actual welding electrode and the actual welding base material, and determines the difference between the virtual welding electrode and the virtual welding base material in the training process. A virtual welding sound can be generated according to the distance, and the speaker can be controlled to output the virtual welding sound.

The welding training simulation device using artificial intelligence analysis technology according to the present invention can provide the effect of allowing trainees to check specific and objective data about the welding training they perform.

In addition, the welding training simulation device using artificial intelligence analysis technology according to the present invention can provide the effect of allowing trainees to conduct welding training in an environment similar to actual welding.

In addition, the welding training simulation device using artificial intelligence analysis technology according to the present invention can provide the effect of enabling welding training equivalent to actual welding training without consuming welding materials.

Figure 1 is a configuration diagram of a welding training simulation device 100 according to the present invention.
Figure 2 is a detailed configuration diagram of the virtual welding gun 140 of the welding training simulation device 100 according to the present invention.
Figure 3 shows a virtual welding mask 200 of the welding training simulation device 100 according to the present invention.
Figure 4 is a flowchart showing an example of a welding training simulation method according to the present invention.
Figure 5 shows an example of a virtual welding flame and bead formation image and the virtual mask perspective image generated according to the welding training simulation method according to the present invention.
Figure 6 is a graph measuring voltage and current in actual arc welding work.
FIG. 7 is a cyclogram to which voltage and current measurement graphs according to the actual arc welding operation of FIG. 6 are applied and a photograph of a high-quality bead generated as a result of the welding process.
Figure 8 shows examples of cyclograms generated as a result of welding training performed by a trainee according to the welding training simulation method according to the present invention.
Figure 9 is a diagram illustrating how the welding training simulation device 100 according to the present invention adjusts the length of the virtual welding rod 143 as welding training time passes in order to implement a working environment similar to the actual welding work process. am.
Figure 10 shows that in order for the welding training simulation device 100 according to the present invention to implement a working environment similar to the actual welding work process, the virtual welding rod 143 is adjusted according to the distance between the virtual welding rod 143 and the virtual welding base material 300. ) This is a diagram to explain controlling the attractive force between the virtual welding base material 300.

In order to fully understand the present invention, its operational or functional advantages, and the objectives achieved by practicing the present invention, reference should be made to the accompanying drawings illustrating preferred embodiments of the present invention and the contents described in the accompanying drawings.

Hereinafter, the present invention will be described in more detail with reference to the attached drawings. Since the present invention can be subject to various changes and have various forms, specific embodiments will be illustrated in the drawings and described in detail in the text. However, this is not intended to limit the present invention to a specific disclosed form, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention.

While describing each drawing, similar reference numerals are used for similar components. In the attached drawings, the dimensions of the structures may be enlarged or reduced from the actual size for clarity of the present invention.

Terms such as first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, a first component may be referred to as a second component without departing from the scope of the present invention, and similarly, the second component may also be referred to as a first component. Singular expressions include plural expressions unless the context clearly dictates otherwise.

In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Additionally, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless clearly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

Figure 1 is a configuration diagram of a welding training simulation device 100 according to the present invention. The welding training simulation device 100 can provide a training environment similar to performing welding training through actual welding work by applying artificial intelligence big data deep learning analysis results to actual welding work.

The welding training simulation device 100 includes a body 110, a simulation control device 120, a setting unit 130, a virtual welding gun 140, a virtual welding mask 200, a display device 160, and a virtual welding base material. Includes 300.

Meanwhile, since the components of the welding training simulation device 100 are not essential, the welding training simulation device 100 may have more components or fewer components. Below we look at each component in more detail.

The simulation control device 120 is equipped with software for performing welding training simulation and can control the operation and function of each component. The welding training simulation device 100 is electrically connected to the virtual welding gun 140, the setting unit 130, and the display device 160, and is connected to the virtual welding mask 200 through short-distance wireless communication. It is done.

The setting unit 130 is a part for setting welding conditions similar to an actual welding device, and is implemented as a touch screen. However, in another example of the present invention, the setting unit 130 may be implemented to include actual physical buttons or levers.

The virtual welding gun 140 can collect various data for welding training simulation and transmit it to the simulation control device 120. The virtual welding gun 140 may be mounted on the mounting portion 150 provided on the body 110.

Figure 2 is a detailed configuration diagram of the virtual welding gun 140 of the welding training simulation device 100 according to the present invention.

The body 141 of the virtual welding gun 140 includes a connecting member 142, a virtual welding rod 143 coupled to the end, and detects the distance between the virtual welding rod 143 and the virtual welding base material 300, and detects the distance between the virtual welding rod 143 and the virtual welding base material 300. It includes a sensing unit 144 that detects the movement path of the welding gun 140.

The virtual welding gun 140 is mounted on the body 110 and includes a virtual welding rod length adjusting unit 145 capable of moving the virtual welding rod 143 forward or backward. For example, the virtual welding rod length adjusting unit 145 may move the virtual welding rod 143 forward or backward by an electric motor. However, the scope of the present invention is not limited thereto.

The virtual welding gun 140 includes an attractive force control unit 146 that can control the attractive force between the virtual welding base material 300 and the virtual welding electrode 143 through current control of the electromagnet. At this time, the virtual welding base material 300 must contain metal that is sensitive to the magnetic force generated by the manpower control unit 146.

The virtual welding gun 140 includes an operation button 147 for starting welding training.

The virtual welding mask 200 has the same shape as an actual welding mask, but can serve to provide information to the trainee according to the welding training simulation process. Information provided here may include visual information, sound information, etc.

The display device 160 can display information input or generated during a welding training simulation process.

Figure 3 shows a virtual welding mask 200 of the welding training simulation device 100 according to the present invention.

The virtual welding mask 200 is wirelessly connected to the simulation control device 120. The virtual welding mask 200 includes a body 210, a display unit 220, a wearing unit 230, a speaker 240, and a button 250.

The display unit 220 may provide image information according to the welding training simulation process inside the virtual welding mask 200 so that the trainee can view it. The display unit 220 is provided in a position corresponding to the viewing window of the actual welding mask, but may not perform an actual viewing function.

The speaker 240 may output voice information according to the welding training simulation process.

Figure 4 is a flowchart showing an example of a welding training simulation method according to the present invention. Hereinafter, the simulation method will be described with reference to the necessary drawings.

First, artificial intelligence big data deep learning analysis is performed on the actual welding device, and the results are stored in the simulation control device 120 (S100).

For example, in actual welding work, artificial intelligence big data deep learning analysis is performed on the actual welding spark and bead formation images according to the distance between the actual welding electrode and the actual welding base material and the moving path of the actual welding gun, and the results are provided to the simulation control device. It is stored at (120).

And in actual welding work, artificial intelligence big data deep learning analysis is performed on the actual mask perspective image where the actual welding flame and bead formation image is shown through the actual welding mask, and the results are stored in the simulation control device 120. It is done.

In addition, artificial intelligence big data deep learning analysis is performed on a cyclogram representing the current-voltage relationship during arc welding in the actual welding device according to the distance between the actual welding electrode and the actual welding base material in actual welding work. and the results are stored in the simulation control device 120.

With the artificial intelligence big data deep learning analysis results stored in the simulation control device 120, the virtual welding rod 143 and the virtual welding base material 300 are used in the training process through the welding training simulation device 100. The distance and the movement path of the virtual welding gun 140 are sensed by the sensing unit 144 (S110) and transmitted to the simulation control device 120.

Then, the simulation control device 120 applies the artificial intelligence big data deep learning analysis results to determine the distance between the virtual welding rod 143 and the virtual welding base material 300 and the movement of the virtual welding gun 140. A virtual welding flame and bead formation image according to the path is generated and provided, and the image is stored (S120).

And the simulation control device 120 applies the artificial intelligence big data deep learning analysis results to generate and provide a virtual mask perspective image for the virtual welding flame and bead formation image and stores it (S130).

The virtual images generated through steps S120 and S130 may be provided through the display device 160 or through the display unit 220 of the virtual welding mask 200.

Figure 5 shows an example of a virtual welding flame and bead formation image generated according to the welding training simulation method according to the present invention.

Although not shown in the drawing, it has been previously described that the simulation control device 120 corresponding to the virtual welding flame and bead formation image can generate a virtual mask perspective image.

Meanwhile, the welding training simulation device 100 may selectively provide the virtual welding flame and bead formation image or the virtual mask perspective image through the display unit 220. This selection can be made by the trainee according to the button 250 of the virtual welding mask 200.

As such, according to the present invention, the trainee can check an image similar to an actual welding mask perspective image through the virtual welding mask 200, and can also check a virtual image of actual welding taking place, providing objective and specific information. As you check, you can perform highly realistic welding training.

Referring again to FIG. 4, the simulation control device 120 applies the results of the artificial intelligence big data deep learning analysis to determine the distance between the virtual welding electrode 143 and the virtual welding base material 300 in the training process. A virtual cyclogram according to the method is generated, and the trainee's welding work proficiency is evaluated based on the virtual cyclogram (S140).

Figure 6 is a graph measuring voltage and current in actual arc welding work. For reference, the voltage and current are measured considering the distance between the actual welding electrode and the actual welding base material in robot welding or similar miscellaneous work by an advanced technician.

FIG. 7 is a cyclogram to which voltage and current measurement graphs according to the actual arc welding operation of FIG. 6 are applied and a photograph of a high-quality bead generated as a result of the welding process. For reference, the cyclogram can be compared with the cyclogram generated through the trainee's welding training and serve as a standard for judging the trainee's welding proficiency.

Figure 8 shows examples of cyclograms generated as a result of welding training performed by a trainee according to the welding training simulation method according to the present invention.

It can be seen that the distribution areas of the cyclograms in FIG. 8 are wider and more diffuse than the cyclograms in FIG. 7. This indicates that the trainee is not skilled in welding work. In this way, according to the present invention, the welding training results can evaluate the trainee's welding work proficiency based on the cyclogram.

Figure 9 is a diagram illustrating how the welding training simulation device 100 according to the present invention adjusts the length of the virtual welding rod 143 as welding training time passes in order to implement a working environment similar to the actual welding work process. am.

Referring to FIG. 9, the welding training simulation device 100 controls the virtual welding rod length adjusting unit 145 mounted inside the virtual welding gun 140, and as the welding training time elapses, the virtual welding rod 143 ) indicates reversing into the interior of the virtual welding gun 140.

This is done according to the distance between the virtual welding electrode 143 and the virtual welding base material 300 during the training process and the virtual reduction length of the virtual welding electrode 143 calculated according to the welding training time.

The virtual reduction length is based on the results of artificial intelligence big data deep learning analysis of the distance between the actual welding electrode and the actual welding base material stored in the simulation control device 120 and the reduction length of the actual welding electrode according to the actual welding time. It can be calculated as follows.

Meanwhile, when the welding training is completed, the virtual welding rod 143, which has retreated into the virtual welding gun 140, advances out of the virtual welding gun 140 to return to its original state.

Figure 10 shows that in order for the welding training simulation device 100 according to the present invention to implement a working environment similar to the actual welding work process, the virtual welding rod 143 is adjusted according to the distance between the virtual welding rod 143 and the virtual welding base material 300. ) is a diagram to explain controlling the attractive force between the virtual welding base material 300.

Referring to FIG. 10, the welding training simulation device 100 operates between the virtual welding rod 143 and the virtual welding base material 300 according to the distance between the virtual welding gun 140 and the virtual welding base material 300. It shows controlling the attraction control unit 146 to adjust the current of the electromagnet to generate attraction between the virtual welding electrode 143 and the virtual welding base material 300 according to the distance.

The manpower is based on the virtual manpower between the virtual welding electrode 143 and the virtual welding base material 300 calculated according to the distance between the virtual welding electrode 143 and the virtual welding base material 300 during the training process.

The virtual manpower is based on the results of artificial intelligence deep learning analysis of the manpower between the actual welding electrode and the actual welding base material according to the distance between the actual welding electrode and the actual welding base material stored in the simulation control device 120. It may have been calculated.

Meanwhile, although not shown in the drawing, the simulation control device 120 applies artificial intelligence big data analysis results to the actual welding sound according to the distance between the actual welding electrode and the actual welding base material, and uses the virtual welding rod in the training process. By generating a virtual welding sound according to the distance between (143) and the virtual welding base material 300 and controlling the speaker 230 mounted on the virtual welding mask 200 to output the virtual welding sound, a more vivid realism is felt. may also be provided.

As discussed above, the welding training simulation device 100 using artificial intelligence analysis technology according to the present invention allows the trainee to check specific and objective data about the welding training he or she performs, and allows the trainee to perform actual welding. It can provide the effect of being able to do welding training in the same environment, and it can provide the effect of being able to do welding training equivalent to actual welding training without consuming welding materials.

As described above, although the present invention has been described with reference to limited embodiments and drawings, the present invention is not limited to the above embodiments, and various modifications and variations can be made from these descriptions by those skilled in the art. This is possible.

Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined by the claims and equivalents thereof as well as the claims described later.

100: Welding training simulation device 110: Body
120: Simulation control device 130: Setting unit
140: Virtual welding gun 150: Mounting part
160: Display device 200: Virtual welding mask
210: body 220: display unit
230: wearing part 240: speaker
250: Button 300: Virtual welding base material

Claims (7)

A virtual welding mask including a display unit corresponding to the viewing window of the actual welding mask, a virtual welding base material; virtual welding gun; Includes a simulation control device and a display device,
The virtual welding gun is,
A virtual welding rod coupled to the end; It includes a sensing unit that detects the distance between the virtual welding rod and the virtual welding base material and the movement path of the virtual welding gun,
The simulation control device is,
By applying artificial intelligence big data deep learning analysis results to the actual welding flame and bead formation images according to the distance between the actual welding rod and the actual welding base material in the actual welding device and the moving path of the actual welding gun,
Generating virtual welding flame and bead formation images according to the distance between the virtual welding rod and the virtual welding base material and the movement path of the virtual welding gun during the training process,
The simulation control device is,
By applying the results of artificial intelligence big data deep learning analysis to a cyclogram representing the current-voltage relationship during arc welding in the actual welding device according to the distance between the actual welding electrode and the actual welding base material,
Generating a virtual cyclogram according to the distance between the virtual welding electrode and the virtual welding base material during the training process, and evaluating the trainee's welding work proficiency based on the virtual cyclogram,
By applying artificial intelligence big data deep learning analysis results to the actual mask perspective image where the actual welding flame and bead formation image is viewed through the actual welding mask,
Generating a virtual mask perspective image for the virtual welding flame and bead formation image,
A welding training simulation device using artificial intelligence analysis technology, characterized in that it can selectively provide the virtual welding flame and bead formation image or the virtual mask perspective image through the display unit.
delete According to paragraph 1,
The virtual welding gun is,
It further includes a virtual welding rod length adjuster capable of moving the virtual welding rod forward or backward,
The simulation control device is,
By applying artificial intelligence big data deep learning analysis results to the distance between the actual welding electrode and the actual welding base material and the reduction length of the actual welding electrode according to the actual welding time,
Calculate the virtual reduction length of the virtual welding electrode according to the distance and welding time between the virtual welding electrode and the virtual welding base material in the training process, and cause the virtual welding electrode to move backward into the virtual welding gun based on the virtual reduction length. A welding training simulation device using artificial intelligence analysis technology, characterized in that it controls the virtual welding rod length adjustment unit.
delete delete According to paragraph 1,
The virtual welding gun is,
It further includes an attractive force control unit capable of controlling the attractive force between the virtual welding base material and the virtual welding electrode through current control of the electromagnet,
The simulation control device is,
By applying the results of artificial intelligence deep learning analysis of the attractive force between the actual welding electrode and the actual welding base material according to the distance between the actual welding electrode and the actual welding base material,
Calculating a virtual force between the virtual welding electrode and the virtual welding material according to the distance between the virtual welding electrode and the virtual welding material during the training process, and controlling the human force control unit to generate a force corresponding to the virtual force. Characterized by a welding training simulation device using artificial intelligence analysis technology.
According to paragraph 1,
The virtual welding mask is,
It is connected to the simulation control device through wireless communication and includes a speaker,
The simulation control device is,
By applying artificial intelligence big data analysis results to the actual welding sound according to the distance between the actual welding electrode and the actual welding base material,
Welding training simulation using artificial intelligence analysis technology, characterized in that it generates a virtual welding sound according to the distance between the virtual welding electrode and the virtual welding base material during the training process, and controls the speaker to output the virtual welding sound. Device.

Images