Welding procedure judgment method and welding procedure judgment device

Abstract

To provide a welding procedure determination method which enables improvement of accuracy of determination of welding quality or evaluation of skill of a worker.SOLUTION: A welding procedure determination method comprises: a step S200 of photographing a weld zone including a molten pool HM during the welding procedure; a step S104 of identifying a primary feature quantity on a shape of at least one of an arc HA and the molten pool HM on the basis of a welding image IP obtained by photographing the weld zone; a step S105 of identifying a secondary feature quantity as a dimensionless amount from a calculation formula using the primary feature quantity as a variable; and a step S107 of determining the welding quality or a skill of the worker on the basis of the secondary feature quantity.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to a welding procedure determination method and a welding procedure determination device. [Background technology]

[0002] Conventionally, there are methods for judging and evaluating the welding quality or the skill of an operator in arc welding such as TIG welding or MAG welding, and applying the results to adaptive control in automatic welding machines, or quantifying the skill in manual welding. Patent Document 1 discloses a technology relating to a welding control method that calculates the amount of change in the root gap by extracting the left and right endpoints of the molten pool from images of the molten pool and its vicinity captured by a visual sensor during welding, and applies the calculated amount of change to the oscillation width of the welding torch or the welding speed. Meanwhile, Patent Document 2 discloses a technology relating to a manual welding work analysis device that evaluates the skill of an operator based on feature values ​​extracted from images of the molten pool and its vicinity captured by a surveillance camera during welding. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-281282 [Patent Document 2] Japanese Patent Application Laid-Open No. 2006-281270 Summary of the Invention [Problem to be solved by the invention]

[0004] In the methods disclosed in Patent Documents 1 and 2, adaptive control of the welding machine and evaluation of the welding worker's skill are based on feature values ​​extracted from images of the molten pool and its vicinity captured during welding. However, welding phenomena are governed by a complex interaction of countless factors with varying degrees of influence. In the technology disclosed in Patent Document 1, the change in root gap is used as the criterion for determining the quality of the weld. Because the root gap is expressed as a dimensional value, if some factor changes between welding operations, the change in the root gap corresponding to that shape may change even if the molten pool shape is the same. Therefore, the change in root gap may not be properly reflected in the oscillation width of the welding torch of the automatic welding machine. On the other hand, in the technology disclosed in Patent Document 2, the monitoring camera is integrally attached to the manual welding torch. Therefore, the captured images are significantly influenced by the welding worker's behavior, making it difficult to standardize the criteria for determining the quality of the skill and reflect them in subsequent judgments and evaluations.

[0005] Therefore, an object of the present disclosure is to provide a welding execution judgment method and a welding execution judgment device that improve the accuracy of judging welding quality or evaluating the skill of a welding installer. [Means for solving the problem]

[0006] A welding execution evaluation method according to one aspect of the present disclosure includes the steps of: photographing a welded portion including a molten pool during welding; identifying a primary feature value relating to the shape of at least one of the arc and the molten pool based on the welding image obtained by photographing the welded portion; identifying a secondary feature value as a dimensionless quantity from a calculation formula using the primary feature value as a variable; and judging the welding quality or evaluating the skill of a welding worker based on the secondary feature value. extracting an arc region corresponding to the arc or a molten pool region corresponding to the molten pool from the welding image as a mask image; With death , The primary feature is identified from multiple feature points extracted based on the shape of the arc region or the weld pool region, or the circumscribing rectangle of the arc region or the circumscribing rectangle of the weld pool region, and the weld pool region is extracted using machine learning that predicts the weld pool endpoints by learning and determining the correct weld pool endpoint positions from the brightness values ​​on multiple search lines of the weld pool extending from the center of gravity of the arc region to the edge of the welding image.

[0007] The above welding work judgment method in teeth, ComplexOne of the feature points may correspond to the tip point of the wire forming the arc, extracted as a depression in the mask image. One of the feature points may correspond to the center of gravity of the arc region. A secondary feature may be set for each welding object, for each item of interest in judging welding quality or in evaluating skills, or for each of multiple welding images obtained by photographing a weld from different photographing positions and directions. The primary feature may be a line passing through two feature points, and the secondary feature may be the slope of the line. The primary feature may be a line segment connecting two feature points, and the secondary feature may be the ratio between the length of one line segment formed by different combinations of two feature points and the length of the other line segment. The primary feature may be the length of each side of a circumscribing rectangle of the arc region, and the secondary feature may be the ratio between the area of ​​the circumscribing rectangle based on a welding image photographed from one photographing position and photographing direction and the area of ​​the circumscribing rectangle based on a welding image photographed from another photographing position and photographing direction. Furthermore, the welding quality or skill may be judged or evaluated based on standard information relating to the pass / fail of the judgment of welding quality or evaluation of skill, which is predefined based on the numerical value of the secondary feature.

[0008] Furthermore, a welding execution judgment device according to another aspect of the present disclosure includes: an imaging device that images a welded portion including a molten pool during welding; a memory unit that stores a calculation formula for a secondary feature quantity as a dimensionless quantity in which a primary feature quantity related to the shape of at least one of the arc and the molten pool is a variable; and a control and calculation unit that identifies the primary feature quantity based on a welding image acquired from the imaging device, identifies the secondary feature quantity based on the primary feature quantity and the calculation formula acquired from the memory unit, and judges the welding quality or evaluates the skill of a welding worker based on the secondary feature quantity. an input unit for inputting a welding object and an item to be focused on in determining welding quality or an item to be focused on in evaluating skills; Equipped with There are a plurality of photographing devices each having a different photographing position and photographing direction, and the control and calculation unit selects from the plurality of photographing devices a photographing device that acquires a welding image to be used for identifying primary feature amounts for each welding object, or for each item to be focused on in determining welding quality or for each item to be focused on in skill evaluation, which are input via the input unit. . [Effects of the Invention]

[0010] According to the present disclosure, it is possible to provide a welding execution judgment method and a welding execution judgment device that improve the accuracy of judging welding quality or evaluating the skill of a welding installer. [Brief explanation of the drawings]

[0011] [Figure 1]1 is a block diagram showing a schematic configuration of a welding construction determination device according to an embodiment; [Figure 2A] FIG. 2 is a perspective view showing the installation position and shooting direction of a first camera. [Figure 2B] FIG. 10 is a perspective view showing the installation position and shooting direction of the second camera. [Figure 2C] FIG. 10 is a perspective view showing the installation position and shooting direction of a third camera. [Figure 2D] FIG. 10 is a perspective view showing the installation position and shooting direction of a fourth camera. [Figure 3] 10 is a flowchart showing a welding execution determination process according to one embodiment. [Figure 4] 10 is a flowchart illustrating a primary feature amount specifying step. [Figure 5A] FIG. 10 is a diagram showing a welding image acquired in a welding image input step. [Figure 5B] FIG. 10 is a diagram showing a mask image displaying each heat quantity region of the arc region and the molten pool region. [Figure 5C] FIG. 5C is a diagram showing an image in which a circumscribing rectangle for each heat quantity region is added to the mask image of FIG. 5B. [Figure 5D] FIG. 10 is a diagram showing an image illustrating an example of feature points related to a molten pool region. [Figure 6A] 1 is a diagram in which a plurality of feature points are plotted on a welding image captured by a first camera. [Figure 6B] 6B is a graph for explaining extraction conditions for each feature point shown in FIG. 6A. [Figure 7A] FIG. 10 is a diagram in which a plurality of feature points are plotted on a welding image captured by a second camera. [Figure 7B] 7B is a graph for explaining extraction conditions for each feature point shown in FIG. 7A. [Figure 8A] FIG. 10 is a diagram in which a plurality of feature points are plotted on a welding image captured by a third camera. [Figure 8B] 8B is a graph for explaining extraction conditions for each feature point shown in FIG. 8A. [Figure 9A] FIG. 10 is a diagram in which a plurality of feature points are plotted on a welding image captured by a fourth camera. [Figure 9B] 9B is a graph for explaining extraction conditions for each feature point shown in FIG. 9A. [Figure 10A] FIG. 10 is a diagram showing a welding image in which primary feature amounts related to secondary feature amount I and the like are displayed. [Figure 10B] 10 is a graph showing a secondary feature value I relative to heat input. [Figure 11A] FIG. 10 is a diagram showing a welding image in which primary feature amounts and the like related to secondary feature amount II are displayed. [Figure 11B] 10 is a graph showing secondary feature quantity II with respect to heat input. [Figure 12A] FIG. 10 is a diagram showing a welding image in which primary feature amounts and the like related to secondary feature amount III are displayed. [Figure 12B] 10 is a graph showing secondary feature quantity III with respect to heat input. [Figure 13A] FIG. 10 is a diagram showing a welding image in which primary feature amounts and the like related to secondary feature amount IV are displayed. [Figure 13B] 10 is a graph showing secondary feature value IV versus welding speed under first standard conditions. [Figure 13C] 10 is a graph showing secondary feature value IV versus welding speed under second standard conditions. [Figure 14] FIG. 10 is a diagram showing a welding image in which primary feature amounts related to secondary feature amount V and the like are displayed. [Figure 15] FIG. 10 is a diagram showing a welding image in which primary feature amounts and the like related to secondary feature amounts VI are displayed. [Figure 16A] FIG. 10 is a diagram showing a welding image in which primary feature amounts and the like related to secondary feature amount VII are displayed. [Figure 16B] FIG. 10 is a diagram showing a welding image in which primary feature amounts and the like related to secondary feature amount VII are displayed. [Figure 17A] FIG. 10 is a diagram in which a plurality of feature points relating to secondary feature amount XII are plotted on a welding image. [Figure 17B] 17B is a graph for explaining extraction conditions for each feature point shown in FIG. 17A. [Figure 18] 10 is a table showing the determination and evaluation results based on secondary feature amounts V to VII. [Figure 19]10 is a table showing the determination and evaluation results based on secondary feature XII. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, several exemplary embodiments will be described with reference to the drawings. Hereinafter, the dimensions, materials, and other specific numerical values ​​shown in each embodiment are merely examples and do not limit the present disclosure unless otherwise specified. Furthermore, elements having substantially the same functions and configurations are assigned the same reference numerals to avoid redundant explanation, and elements not directly related to the present disclosure are not shown.

[0013] 1 is a block diagram showing a schematic configuration of a welding performance judgment device 1 according to one embodiment. The welding performance judgment device 1 judges the welding quality or evaluates the skill of a welding worker based on an image obtained by photographing a molten pool during welding.

[0014] The welding to be judged or evaluated by the welding execution judgment device 1 may be welding performed by an automatic welding machine or manual welding performed by a worker. Here, manual welding includes so-called semi-automatic welding. Examples of welding methods that can be judged or evaluated include arc welding, such as MAG welding, MIG welding, and TIG welding. In this embodiment, the welding execution judgment device 1 judges the quality or evaluates the skill of welding performed using a welding machine 80, which is an automatic or semi-automatic welding machine employing MAG welding, for example. The welding machine 80 includes a welding torch 81 and a wire feeder (not shown) that automatically feeds wire 82 to the welding torch 81 (see FIG. 2A, etc.). The wire 82 is, for example, a solid wire, and is fed from the tip of the welding torch 81 toward a welding object 90 (see FIG. 2A, etc.). Welding progresses when an arc generated between the wire 82 and the welding object 90, which serves as a welded member (base metal), melts the wire 82 and the welding object 90. Welding torch 81 supplies shielding gas toward the weld on welding object 90. The shielding gas is an active gas such as carbon dioxide gas, and shields the periphery of the arc and molten pool from the atmosphere.

[0015] The welding object 90 may be the product itself or a component that constitutes part of the product. Alternatively, the welding object 90 may be, for example, a test piece used in a skill certification test under the Japanese Industrial Standards (JIS). The shape of the welding object 90 is, for example, a flat plate that is joined together by butt welding. However, the final shape of the component produced by welding is not limited to a flat plate shape, and may also be a tubular shape.

[0016] The welding construction judgment device 1 includes an imaging device 10, a control and calculation unit 11, a storage unit 12, an input unit 13, and an output unit 14.

[0017] The imaging device 10 photographs the welded portion, including the molten pool, formed on the welding object 90 while the welding object 90 is being welded by the welding machine 80. The imaging device 10 is, for example, a CCD camera. There are multiple imaging devices 10 so that they can photograph the welded portion from different viewpoints. In this embodiment, as an example, a total of four imaging devices 10 are used: a first camera 10a, a second camera 10b, a third camera 10c, and a fourth camera 10d. Hereinafter, the images captured by the imaging devices 10 will be referred to as "welding images."

[0018] 2A to 2D are perspective views illustrating the installation positions and photographing directions of the respective photographing devices 10 relative to the molten pool in the welding target 90. 2A to 2D show the plate-shaped welding target 90, a welding torch 81 of a welding machine 80, and a wire 82 supplied from the welding torch 81 to the welded portion in the welding target 90. 2A to 2D also show the welding direction D W is indicated by an open arrow.

[0019] Here, XY coordinate axes to be referred to in the following drawings are set. In this embodiment, the XY plane is assumed to be a plane parallel to the main plane of the plate-shaped welding object 90. The X axis is along the extension direction of the linear route provided on the welding object 90. That is, the welding direction D in this embodiment W is a direction roughly along the X axis. The Y axis is perpendicular to the X axis.

[0020] 2A is a diagram showing the installation position and shooting direction of the first camera 10a. The shooting direction of the first camera 10a is set to the welding direction D W Horizontal angle θ from the left side of H = 45° and vertical angle θ V In Figure 2A, the welding direction D W On the left side of the horizontal angle θ H The broken line is displayed at the position where the shooting distance L = 0°. S = 250 mm.

[0021] 2B is a diagram showing the installation position and shooting direction of the second camera 10b. The shooting direction of the second camera 10b is set to the welding direction D W On the left side of the V The second camera 10b is set to a direction in which the angle θ is 45°. S = 250 mm.

[0022] 2C is a diagram showing the installation position and shooting direction of the third camera 10c. The shooting direction of the third camera 10c is set to the welding direction D W In front of the vertical angle θ V = 45°. The third camera 10c satisfies the shooting direction condition and is positioned at a shooting distance L S = 250 mm.

[0023] 2D is a diagram showing the installation position and shooting direction of the fourth camera 10d. The shooting direction of the fourth camera 10d is set to the welding direction D W In front of the vertical angle θ V = 15°. The fourth camera 10d satisfies the shooting direction condition and has a shooting distance L S = 250 mm.

[0024] Note that when the welding construction judgment device 1 judges or evaluates a welding construction object 90, an evaluation object, or standard conditions are limited to specific ones, not all four of the image capturing devices 10 are necessarily used. Therefore, an image capturing device 10 that is not expected to be used in advance does not need to be provided in the welding construction judgment device 1. On the other hand, even an image capturing device 10 that is not expected to be used in advance may be provided in the welding construction judgment device 1 as a spare in case, for example, a malfunction occurs in one of the other image capturing devices 10. In this case, feature amounts based on the welding image that would be obtained from the malfunctioning image capturing device 10 can be supplemented with feature amounts based on the welding image obtained from the spare image capturing device 10.

[0025] Control and calculation unit 11 is, for example, a CPU (Central Processing Unit) and executes a program related to the welding performance evaluation step as the welding performance evaluation method according to this embodiment. Control and calculation unit 11 is electrically connected to all of image capture devices 10, memory unit 12, and input unit 13. When the welding performance evaluation step is executed to evaluate the welding quality of an automatic welding machine, control and calculation unit 11 may be electrically connected to welding machine 80 in order to modify the performance conditions of the automatic welding machine in real time based on the evaluation results. When the welding performance evaluation step is executed to evaluate the skill of a welding worker, control and calculation unit 11 may be electrically connected to output unit 14 in order to display the evaluation results to the welding worker or an operator operating welding performance evaluation device 1.

[0026] The storage unit 12 is, for example, a semiconductor memory or a magnetic storage device such as an HDD (hard disk drive), and stores (preserves) programs, databases, etc. The control and calculation unit 11 can read out the programs and data stored in the storage unit 12 as needed. The control and calculation unit 11 can also write new data to the storage unit 12 as needed.

[0027] The memory unit 12 also has a program storage unit 15 and a database storage unit 16. The program storage unit 15 stores at least a control program related to a series of controls in the welding construction evaluation process and an image processing program, including a machine learning program, executed in the primary feature quantity identification process S104 (see FIG. 3). The database storage unit 16 stores at least various databases queried in the welding construction evaluation process. The databases that can be stored in the program storage unit 15 are a standard condition database queried in the standard condition acquisition process S101 (see FIG. 3) and a reference information database that stores reference information queried in the reference information acquisition process S106 (see FIG. 3). Details of the standard condition database and the reference information database will be described later together with the description of the standard condition acquisition process S101 or the reference information acquisition process S106. Furthermore, the memory unit 12 saves welding images captured by the imaging device 10.

[0028] The input unit 13 is, for example, an operation input device such as a keyboard or a touch panel, a receiving device that receives information from an external device, or an input port that reads information from a portable memory device such as a memory card. An operator can directly input various pieces of information through the input unit 13 as an operation input device. Alternatively, the control and calculation unit 11 can receive various pieces of information from an external server or the like via a communication network such as a LAN or the Internet from the input unit 13 as a receiving device. Furthermore, the control and calculation unit 11 can transfer various pieces of information from a memory device through the input unit 13 as an input port. The information that can be input through the input unit 13 is the initial conditions set in the initial condition setting step S100 (see FIG. 3). Details of the initial conditions will be described later together with the explanation of the initial condition setting step S100.

[0029] The output unit 14 is a display unit such as a monitor, a transmitting device that transmits information to the outside, or an output port that writes information to a memory device. The control and calculation unit 11 can display the judgment and evaluation results obtained by the welding construction judgment process on the output unit 14 as a display unit, so that the builder or operator can directly recognize them. Alternatively, the control and calculation unit 11 can transmit the judgment and evaluation results from the output unit 14 as a transmitting device to an external server or the like via a communication network. Furthermore, the control and calculation unit 11 can transfer the judgment and evaluation results from the output unit 14 as an output port to a memory device.

[0030] Next, the operation of the welding construction judgment method and the welding construction judgment device 1 according to this embodiment will be described.

[0031] 3 is a flowchart showing a welding construction judgment process as a welding construction judgment method according to this embodiment. The welding construction judgment process includes a series of steps according to the flowchart shown in FIG. 3 and is executed by control calculation unit 11 as a control program of welding construction judgment device 1.

[0032] When control calculation unit 11 starts executing the welding construction determination process, it first executes an initial condition setting process S100. In the initial condition setting process S100, control calculation unit 11 sets various initial conditions based on information input by an operator via input unit 13. The initial conditions are, for example, a welding construction object 90 and an object to be determined and evaluated.

[0033] Welding object 90 is set from the perspective of the type or specific shape of the welded joint, etc. For example, when judging the welding quality of welding machine 80 as an automatic welding machine, the product itself may be selected as welding object 90. Alternatively, when evaluating the skill of a worker who operates welding machine 80 as a semi-automatic welding machine, various test pieces may be selected as welding object 90.

[0034] In the following examples of this embodiment, the welding object 90 is set to conform to the dimensions of the test piece used in the JIS Trade Mark Test. Specifically, as shown in FIGS. 2A to 2D , the welding object 90 is a pair of plate materials that are pre-processed to have a V-shaped groove and are butt-welded together with the grooved ends as the joining surfaces. For example, three types of plate materials, each with a different thickness, are used as the welding object 90: a thin plate, a medium plate, and a thick plate. The thickness of the thin plate is 3.2 mm. The welding between the thin plates is performed under conditions of a 90° groove angle and a gap (root spacing) of approximately 2 mm. The thickness of the medium plate is 9.0 mm. The welding between the medium plates is performed under conditions of a 70° groove angle and a 5 mm gap. The thickness of the thick plate is 19.0 mm. Welding between thick plates is performed under conditions where the groove angle is 70° and the gap is approximately 5 mm.

[0035] The object of judgment and evaluation is set as a specific item of focus regarding welding quality or skill. For example, the object of judgment and evaluation regarding welding quality (welded joint quality) is the formation of back waves.

[0036] Next, the control and calculation unit 11 executes a standard condition acquisition step S101. In the standard condition acquisition step S101, the control and calculation unit 11 acquires and sets standard conditions corresponding to the initial conditions set in the initial condition setting step S100 by consulting a standard condition database. The standard conditions are, for example, the welding current, welding voltage, welding speed, and angle of the welding torch 81 for each initial condition, such as the type of weld joint or the plate thickness or material of the welding object 90, or a calculation formula for secondary feature quantities corresponding to the object to be judged and evaluated. Note that the secondary feature quantities in this embodiment will be described later together with the secondary feature quantity identification step S105. The standard condition database is pre-stored in the database storage unit 16 included in the memory unit 12. The calculation formula for secondary feature quantities stored in the standard condition database may be a formula identified in the secondary feature quantity identification step S105 when the welding operation judgment step was performed during a previous welding operation and persistently stored.

[0037] Next, control calculation unit 11 starts welding (start welding S102). When welding is performed by welding machine 80 as an automatic welding machine, control calculation unit 11 may start the operation of welding machine 80. On the other hand, when welding is performed by a worker as manual welding, control calculation unit 11 may make the worker aware that it is now possible to start welding by, for example, displaying on output unit 14 as a display unit.

[0038] Next, the control and calculation unit 11 executes a welded portion photographing step S103. In the welded portion photographing step S103, the control and calculation unit 11 causes each of the photographing devices 10, namely, the first camera 10a, the second camera 10b, the third camera 10c, and the fourth camera 10d, to photograph the welded portion during welding. As described above, the welded portion to be photographed by the photographing devices 10 includes the molten pool formed in the welding object 90. The control and calculation unit 11 stores the photographed welding images in the memory unit 12.

[0039] Next, the control and calculation unit 11 executes a primary feature amount specifying step S104. Fig. 4 is a flowchart showing the primary feature amount specifying step S104. The primary feature amount specifying step S104 is executed by the control and calculation unit 11 as an image processing program including a series of steps in accordance with the flowchart shown in Fig. 4. Then, in the primary feature amount specifying step S104, the control and calculation unit 11 finally specifies the primary feature amount based on the welding image.

[0040] 5A to 5D show, as an example, a welding image I captured by the second camera 10b. P 5B to 5D are diagrams illustrating images acquired or extracted in each step included in the primary feature amount specifying step S104 based on the welding image I shown in FIG. P The area corresponding to the arc in the figure is called "arc area A" C " and the area corresponding to the molten pool (molten metal) is referred to as "molten pool area M P ". Arc region A C and the molten pool area M P The other areas are the background and are shown in black in the figure.

[0041] Here, the primary feature quantity refers to a function for directly recognizing the weld including the molten pool, i.e., a quantity representing the shape of the heat source region such as the molten pool, obtained from each imaging device 10 that images the weld. The primary feature quantity is defined in advance for each secondary feature quantity described below. For example, the primary feature quantity may be the position of one feature point or the length of a line segment connecting two feature points. Alternatively, the primary feature quantity may be the area of ​​a region consisting of multiple line segments or curves.

[0042] When the control and calculation unit 11 starts the execution of the primary feature amount specifying step S104, it first executes the welding image input step S200. In the welding image input step S200, the control and calculation unit 11 inputs the welding images I captured by each of the image capturing devices 10 in the welded part photographing step S103. P Among them, welding image I is required to identify the desired primary feature. P is acquired from the storage unit 12.

[0043] FIG. 5A shows the welding image I acquired in the welding image input step S200. P In the example shown in FIG. 5A, the welding image I P Although it is shown in grayscale, it is actually a color image. Welding Image I P Well, Arc H A is displayed in white or near-white, and the molten pool H M is generally shown in grey, with a black background.

[0044] Next, the control and calculation unit 11 executes a filtering process step S201. In the filtering process step S201, the control and calculation unit 11 filters the welding image I obtained in the welding image input process S200. P For example, a Gaussian filter is applied to the welding image I P Suppresses fluctuations in the specific heat field.

[0045] Next, the control and calculation unit 11 executes an arc region extraction step S202. In the arc region extraction step S202, the control and calculation unit 11 extracts the filtered welding image I PBy extracting a specific color component, for example, the blue component, from the arc area A C At this time, the control calculation unit 11 binarizes the image of the blue component with a preset brightness threshold value, and finally extracts the arc region A C may be extracted.

[0046] Next, the control and calculation unit 11 executes a weld pool region extraction step S203. In the weld pool region extraction step S203, the control and calculation unit 11 executes a machine learning program that employs a learning model that predicts the end points of the weld pool from the waveform on the search line, thereby extracting the weld pool region M P In this case, deep learning, which uses mean squared error (MSE) as an evaluation function, can be adopted as the machine learning method in the machine learning program.

[0047] The control and calculation unit 11 executes a machine learning program to learn and determine, for example, the correct molten pool end positions (1717 images × 128 search lines = approximately 220,000 data). Specifically, the control and calculation unit 11 calculates the arc region A extracted in the arc region extraction step S202. C Calculate the center of gravity of the arc area A C Then, 128 search lines of the molten pool are generated around the center of gravity of the image to the edge of the image. Next, the control and calculation unit 11 calculates the end points of the molten pool on each search line according to the seven patterns classified by the waveform shape of the brightness values ​​on the search lines. Then, the control and calculation unit 11 connects the calculated end points of the molten pool between the points on the search lines that are adjacent to each other, and calculates the molten pool area M P Extract as.

[0048] The seven patterns mentioned above for calculating the end points of the weld pool are as follows: Pattern 1 is a waveform shape in which an outline appears after a continuous area of ​​only the weld pool. Pattern 2 is a waveform shape in which yellow areas appear two or more times. Pattern 3 is a waveform shape in which a yellow area with high heat is created around the arc. Pattern 4 is a waveform shape in which the edges of the arc and weld pool are close to each other. Pattern 5 is a waveform shape in which the shielding gas enters the background once and then re-emerges. Pattern 6 is a waveform shape in which the shielding gas spreads outside the weld pool. Pattern 7 is a waveform shape in which the brightness value of the weld pool outline is close to the background.

[0049] FIG. 5B shows the arc region A extracted in the arc region extraction step S202. C and the molten pool area M extracted in the molten pool area extraction step S203. P 1 is a diagram showing an image displaying each heat quantity region of arc region A. C and the molten pool area M P is the mask image I as shown in Figure 5B. M It is expressed as:

[0050] Next, the control operation unit 11 executes a circumscribing rectangle extraction step S204. In the circumscribing rectangle extraction step S204, the control operation unit 11 extracts the arc region A extracted in the arc region extraction step S202. C From the mask, arc area A C The circumscribing rectangle R A The control calculation unit 11 extracts the molten pool region M extracted in the molten pool region extraction step S203. P From the mask, the molten pool area M P The circumscribing rectangle R B Extract.

[0051] Figure 5C shows the mask image I of Figure 5B. M , arc region A C The circumscribing rectangle R A and the molten pool area M P The circumscribing rectangle R B The figure shows an image with the circumscribing rectangle R B The left side of the mask is the minimum value X in the X direction, with the bottom left of the image as the origin.M1 The right side is the maximum value of the mask in the X direction, X M2 The bottom side is the minimum Y value of the mask. M1 The upper side is the maximum Y value of the mask in the Y direction. M2 The rectangles are extracted as rectangles that pass through each of the circumscribing rectangles R B The mask for the molten pool area M P The mask of the circumscribing rectangle R A is the bounding box R B It is extracted using the same method as the extraction method of .

[0052] Next, the control and calculation unit 11 executes a feature point extraction step S205. In the feature point extraction step S205, the control and calculation unit 11 extracts the circumscribing rectangle R extracted in the circumscribing rectangle extraction step S204. A and circumscribed rectangle R B Based on this, feature points to be used in subsequent calculation of primary feature amounts are extracted.

[0053] Figure 5D shows the circumscribing rectangle R B The molten pool area M is extracted based on P 5D is a diagram showing an example of an image of four feature points, namely, feature point P 1A , feature point P 1B , feature point P 2A and feature point P 2B corresponds to the feature points shown in FIG. 7B, which will be exemplified below.

[0054] The feature points extracted in the feature point extraction step S205 are the welding image I P Therefore, the extraction condition of the feature points is based on the welding image I P Conditions affecting welding image I P Various possibilities are possible depending on the type of imaging device 10 that captured the image and the type of welding object 90. Below, examples of feature points and their extraction conditions for each imaging device 10 and welding object 90 are given.

[0055] 6A and 6B are diagrams relating to a first example of feature points and their extraction conditions extracted from a welding image captured by the first camera 10a and in which the welding object 90 is an intermediate plate.

[0056] 6A is a diagram showing a welding image on which a plurality of feature points are plotted. The feature points according to the first example are, for example, feature points P 1A , feature point P 1B , feature point P2, feature point P 3A , feature point P 3B , feature point P 4A and feature point P 4B There are a total of seven feature points. 1A is the front end point of the molten pool region. 1B is the rear end point of the molten pool region. The characteristic point P2 is the midpoint between the front and rear end points of the molten pool region. 3A is the left end point of the molten pool area. 3B is the right end point of the molten pool area. 4A is the upper end point of the molten pool region. 4B is the lower end point of the weld pool region. Hereinafter, the expressions "front / back," "left / right," and "up / down" used to indicate each characteristic point are used to simply distinguish the positional relationship between multiple characteristic points. For example, W It is not based on the exact orientation relative to the weld pool or the exact shape of the weld pool area.

[0057] 6B is a graph for explaining the extraction conditions of each feature point extracted based on the mask of the molten pool region. Each mask of the arc region and the molten pool region in FIG. 6B is the same as that of the arc region A shown in FIG. 5C etc. C or molten pool area M P The circumscribing rectangle of the molten pool area is extracted based on the welding image shown in FIG. 6A. The circumscribing rectangle of the molten pool area M P The circumscribing rectangle R B In addition, the minimum value in the X direction of the circumscribing rectangle of the molten pool area is set to X M1 and the maximum value in the X direction is X M2 and the minimum value in the Y direction is Y M1 and the maximum value in the Y direction is Y M2and are written as follows, respectively.

[0058] Referring to FIG. 6B, the extraction conditions for the feature points according to the first example are as follows: 1A is the bottom left coordinate of the circumscribing rectangle of the weld pool area (X M1 ,Y M1 ) to the upper right coordinate (X M2 ,Y M2 ) and the contour of the mask of the weld pool area, the coordinates (X M1 ,Y M1 ) is extracted as the point closest to the feature point P 1B Similarly, the coordinate (X M1 ,Y M1 ) to coordinates (X M2 ,Y M2 ) and the contour of the mask of the weld pool area, the coordinates (X M2 ,Y M2 ) is extracted as the point closest to feature point P 1A and feature point P 1B The feature point P is extracted as the midpoint between 3A is extracted as the intersection of a half line extending from the characteristic point P2 in the negative direction of the X axis and the contour of the mask of the molten pool region. 3B is extracted as the intersection of a half line extending from the characteristic point P2 in the positive direction of the X axis and the contour of the mask of the molten pool region. 4A is extracted as the intersection of a half line extending from the characteristic point P2 in the positive direction of the Y axis and the contour of the mask of the molten pool region. 4B is extracted as the intersection of a half line extending from the feature point P2 in the negative direction of the Y axis and the contour of the mask of the molten pool region. Note that Figures 6A and 6B illustrate line segments connecting two feature points, which are referenced when extracting each feature point.

[0059] 7A and 7B are diagrams relating to a second example of feature points and their extraction conditions extracted from a welding image captured by the second camera 10b and in which the welding object 90 is an intermediate plate.

[0060] 7A is a diagram showing a welding image on which a plurality of feature points are plotted. The feature points according to the second example are, for example, feature points P 1A , feature point P 1B , feature point P 2A , feature point P 2B and feature point P3, for a total of five. 1A is the front end point of the molten pool region. 1B is the rear end point of the molten pool region. 2A is the left end point of the molten pool area. 2B The characteristic point P3 is the tip point of the wire 82.

[0061] 7B is a graph for explaining the extraction conditions for each feature point extracted based on the masks of the arc region and the molten pool region. The drawing conditions in FIG. 7B are the same as those in FIG. 6B. The extraction conditions for the feature points in the second example are as follows: Feature point P 1A is X=X M1 The feature point P is extracted as the point where Y is the intermediate value from the point group. 1B is X=X M2 The feature point P is extracted as the point where Y is the intermediate value from the point group. 2A is Y=Y M2 The feature point P is extracted as the point where X is the intermediate value from the point group. 2B is Y=Y M1 The feature point P3 is extracted as the bottom edge of the depression in the mask at the top of the arc region.

[0062] Here, the control and calculation unit 11 may identify the depression of the mask to be referenced when extracting the feature point P3 by, for example, analyzing pixel values ​​along the X direction for the upper half of the mask of the arc region, where the pixel values ​​on the mask are 255 and the pixel values ​​in the background are 0 (zero). In this case, the control and calculation unit 11 extracts, as a depression candidate, a position obtained by averaging the X coordinates from the coordinates where the pixel values ​​on one line are 0 (zero). Next, the control and calculation unit 11 narrows down the depression candidates based on the conditions that the depression must consist of three or more consecutive lines in the Y direction and that the bottom ends of the consecutive lines in the Y direction are used as the end points of the depression. Then, from the final depression candidates, the control and calculation unit 11 selects the one whose X coordinate is closest to the center of gravity of the arc region as the depression of the mask to be referenced when extracting the feature point P3.

[0063] 8A and 8B are diagrams relating to a third example of feature points and their extraction conditions extracted from a welding image captured by the third camera 10c and in which the welding object 90 is an intermediate plate.

[0064] 8A is a diagram showing a welding image on which a plurality of feature points are plotted. The feature points according to the third example are, for example, feature points P 1A , feature point P 1B , feature point P 2A , feature point P 2B and feature point P3, for a total of five. 1A is the upper end point of the molten pool region. 1B is the lower end point of the molten pool region. 2A is the left end point of the molten pool area. 2B The characteristic point P3 is the tip point of the wire 82.

[0065] 8B is a graph for explaining the extraction conditions for each feature point extracted based on the masks of the arc region and the molten pool region. The drawing conditions in FIG. 8B are the same as those in FIG. 6B. The extraction conditions for the feature points in the third example are as follows: Feature point P 1A is Y=Y M2 The feature point P is extracted as the point where X is the intermediate value from the point group.1B is Y=Y M1 The feature point P is extracted as the point where X is the intermediate value from the point group. 2A is X=X M1 The feature point P is extracted as the point where Y is the intermediate value from the point group. 2B is X=X M2 The feature point P3 is extracted as the bottom edge of the depression in the mask at the top of the arc region, as in the second example above.

[0066] 9A and 9B are diagrams relating to a fourth example of feature points and their extraction conditions extracted from a welding image captured by the fourth camera 10d and in which the welding object 90 is an intermediate plate.

[0067] 9A is a diagram showing a welding image on which a plurality of feature points are plotted. The feature points according to the fourth example include, for example, feature point P1, feature point P 2A , feature point P 2B , P3, and P4. Feature point P1 is the front end point of the molten pool area. 2A is the left end point of the molten pool area. 2B is the right end point of the molten pool region. Characteristic point P3 is the tip point of the wire 82. Characteristic point P4 is the bottom end point of the arc region.

[0068] 9B is a graph for explaining the extraction conditions for each feature point extracted based on the masks for the arc region and the molten pool region. The drawing conditions in FIG. 9B are the same as those in FIG. 6B. However, in FIG. 9B, the minimum value in the Y direction of the arc region is set as Y A1 The extraction conditions for the feature points in the fourth example are as follows: Feature point P1 is expressed as Y=Y M1 The feature point P is extracted as the point where X is the intermediate value from the point group. 2A is X=X M1 The feature point P is extracted as the point where Y is the intermediate value from the point group. 2B is X=X M2The feature point P3 is extracted as the bottom edge of the depression in the mask at the top of the arc region, just like in the second example above. The feature point P4 is extracted as the point where Y=Y A1 The point where X is the intermediate value is extracted from the group of points.

[0069] Up to this point, an example of feature points and their extraction conditions has been described for the case where the welding performance object 90 is a medium-sized plate. However, in the feature point extraction step S205, feature points are similarly extracted even when the welding performance object 90 is, for example, a thick plate, depending on the object to be judged and evaluated. Feature points and their extraction conditions for the case where the welding performance object 90 is a thick plate will be exemplified together in the explanation of secondary feature quantity XII using Figures 17A and 17B below.

[0070] Then, the control and calculation unit 11 executes a primary feature value calculation step S206 following the feature point extraction step S205. In the primary feature value calculation step S206, the control and calculation unit 11 calculates the arc region A extracted in the circumscribing rectangle extraction step S204. C The circumscribing rectangle R A or molten pool area M P The circumscribing rectangle R B Alternatively, the primary feature quantity is calculated using the feature points extracted in the feature point extraction step S205. Here, the primary feature quantity is defined from the secondary feature quantities selected based on the judgment / evaluation target set in the initial condition setting step S100. Therefore, specific primary feature quantities that can be calculated in the primary feature quantity calculation step S206 will be exemplified below for each secondary feature quantity in the description of the secondary feature quantities identified in the secondary feature quantity identification step S105. After completing the primary feature quantity calculation step S206, the control and calculation unit 11 ends the primary feature quantity identification step S104 in the welding construction judgment step.

[0071] Next, the control and calculation unit 11 executes the secondary feature quantity specifying step S105 following the primary feature quantity specifying step S104. The secondary feature quantity refers to a quantity obtained from a calculation formula (calculation formula for secondary feature quantity) using the primary feature quantity as a variable. The secondary feature quantity may be a dimensionless quantity such as a ratio between primary feature quantities or the slope of a line segment connecting two feature points. In the secondary feature quantity specifying step S105, the control and calculation unit 11 calculates the secondary feature quantity using the calculation formula for secondary feature quantity acquired in the standard condition acquisition step S101 according to the judgment / evaluation object. Below, specific secondary feature quantities selected and specified for each welding construction object 90 and judgment / evaluation object are exemplified.

[0072] 10A and 10B are diagrams relating to secondary feature value I when the welding object 90 is a middle plate and the object of judgment / evaluation is the presence or absence of insufficient fusion related to the stability of the movement of the molten pool.

[0073] 10A is a diagram showing the primary feature amount and the line segment related to the calculation formula of the secondary feature amount I on the welding image used to identify the primary feature amount. The primary feature amount used to identify the secondary feature amount I is the feature point P obtained based on the welding image captured by the second camera 10b. 1A and feature point P 1B The welding image shown in FIG. 10A corresponds to the welding image shown in FIG. 7A. That is, the characteristic points P 1A is the front end point of the molten pool region. 1B is the rear end point of the molten pool region. In this case, the calculation formula for the secondary feature value I is 1A and feature point P 1B The final calculated secondary feature value I is the equation of the line that passes through the feature point P 1A and feature point P 1B is the slope of the line passing through and is a dimensionless quantity.

[0074] Figures 11A and 11B are diagrams relating to secondary feature value II when the welding target 90 is a middle plate and the object of judgment / evaluation is the presence or absence of poor fusion related to the followability of the molten pool to the wire 82.

[0075] 11A is a diagram showing the primary feature amount and the line segments related to the calculation formula of the secondary feature amount II on the welding image used to identify the primary feature amount. The primary feature amount used to identify the secondary feature amount II is the feature point P3 and the feature point P4 obtained based on the welding image captured by the third camera 10c. 1B The welding image shown in FIG. 11A corresponds to the welding image shown in FIG. 8A. That is, the characteristic point P3 is the tip point of the wire 82. The characteristic point P 1B is the front end point of the molten pool region. In this case, the calculation formula for the secondary feature value II is 1B The final calculated secondary feature value II is the equation of the straight line passing through the feature point P3 and the feature point P 1B is the slope of the line passing through and is a dimensionless quantity.

[0076] 12A and 12B are diagrams relating to secondary feature quantity III when the welding execution object 90 is a middle plate and the object to be judged and evaluated is heat input.

[0077] 12A is a diagram showing the primary feature amount and the circumscribing rectangle related to the calculation formula of the secondary feature amount III on the welding image used to identify the primary feature amount. The primary feature amount used to identify the secondary feature amount III is the circumscribing rectangle R of the weld pool area obtained based on the welding image captured by the second camera 10b. B In other words, when identifying the secondary feature quantity III, the length of each side of the circumscribing rectangle R extracted in the circumscribing rectangle extraction step S204 is B It is sufficient to refer to the welding image shown in FIG. 12A, and no feature points are required. The welding image shown in FIG. 12A also corresponds to the welding image shown in FIG. 7A. In this case, the calculation formula for the secondary feature amount III is B The length of each side of the circumscribing rectangle R B The final secondary feature value III is calculated by the formula for calculating the area of ​​the circumscribing rectangle R B is the area.

[0078] 13A, 13B, and 13C are diagrams relating to secondary feature values ​​IV when the welding operation target 90 is a middle plate and the object to be judged and evaluated is the welding speed.

[0079] 13A is a diagram showing the primary feature values ​​and the line segments related to the calculation formula of the secondary feature value IV on the welding image used to identify the primary feature values. The primary feature value used to identify the secondary feature value IV is calculated from four feature points obtained based on the welding image captured by the second camera 10b. Specifically, the primary feature value is calculated from the feature point P corresponding to the length of the molten pool. 1A and feature point P 1B The length of the line connecting these points and the characteristic point P 2A and feature point P 2B and the length of the line segment connecting the feature points P 1A is the front end point of the molten pool region. 1B is the rear end point of the molten pool region. 2A is the left end point of the molten pool area. 2B is the right end point of the molten pool area. In this case, the calculation formula for the secondary feature value IV is 1A and feature point P 1B The length of the line connecting the feature point P 2A and feature point P 2B The final secondary feature value IV is the ratio of the length of the molten pool to the width (aspect ratio) of the feature point P 1A and feature point P 1B The length of the line connecting the feature point P 2A and feature point P 2B It is the ratio of the length of the line segment connecting the points and is a dimensionless quantity.

[0080] Up to this point, examples of secondary feature amounts when the welding object 90 is a medium plate have been described. Next, examples of secondary feature amounts when the welding object 90 is a thin plate or a thick plate will be described.

[0081] 14, 15, 16A, and 16B are diagrams relating to secondary feature values ​​relating to whether the welding object 90 is a thin plate and the object of judgment / evaluation is, for example, a back-beam formation property, that is classified as "burn-through," "sound weld," or "insufficient back-beam." FIG. 14 is a diagram relating to secondary feature value V. FIG. 15 is a diagram relating to secondary feature value VI. FIGS. 16A and 16B are diagrams relating to secondary feature value VII.

[0082] FIG. 14 shows the primary feature values ​​and lengths related to the calculation formula for the secondary feature value V on the welding image used to identify the primary feature values. The primary feature values ​​used to identify the secondary feature value V are calculated from three feature points obtained based on the welding image captured by the fourth camera 10d. Specifically, the primary feature values ​​are a first length L1 between the tip point of the wire 82 and the rear end point of the weld pool region, which corresponds to the length of the upper part of the groove of the weld pool, and a second length L2 between the tip point of the wire 82 and the front end point of the weld pool region, which corresponds to the length of the lower part of the groove of the weld pool. In other words, the three feature points here correspond to the front end point of the weld pool region, the rear end point of the weld pool region, and the tip point of the wire 82. In this case, the calculation formula for the secondary feature value V is a formula for calculating the ratio expressed as (first length L1 / second length L2). The final calculated secondary feature value V is expressed as (first length L1 / second length L2) (length of upper part of groove of molten pool / length of lower part of groove of molten pool), and is a dimensionless quantity.

[0083] FIG. 15 shows the primary feature values ​​and lengths related to the calculation formula for the secondary feature value VI on the welding image used to identify the primary feature values. The primary feature values ​​used to identify the secondary feature value VI are calculated from four feature points obtained based on the welding image captured by the fourth camera 10d. Specifically, the primary feature values ​​are a third length L3 between the left end point of the weld pool region and the right end point of the weld pool region, which corresponds to the width of the weld pool, and a fourth length L4 between the tip point of the wire 82 and the front end point of the weld pool region, which corresponds to the length of the lower part of the groove of the weld pool. In other words, the four feature points here correspond to the left end point of the weld pool region, the right end point of the weld pool region, the front end point of the weld pool region, and the tip point of the wire 82. In this case, the calculation formula for the secondary feature value VI is a formula for calculating the ratio expressed as (third length L3 / fourth length L4). The finally calculated secondary feature value VI is expressed as (third length L3 / fourth length L4) (width of molten pool / length of bottom of groove of molten pool), and is a dimensionless quantity.

[0084] 16A and 16B are diagrams showing the primary feature amount and a circumscribing rectangle related to the calculation formula of the secondary feature amount VII on the welding image used to identify the primary feature amount. The primary feature amount used to identify the secondary feature amount VII is first calculated by calculating the circumscribing rectangle R of the arc region obtained based on the welding image captured by the second camera 10b shown in FIG. A1 The primary feature used to identify the secondary feature VII is the length of each side of the circumscribing rectangle R of the arc region obtained based on the welding image captured by the fourth camera 10d, as shown in FIG. 16B. A2 is the length of each side of the circumscribing rectangle R A1 The welding image for identifying the circumscribing rectangle R can be considered as being taken from above. A2 The welding image for identifying the secondary feature amount VII can be considered to have been photographed from the front. A In this case, the calculation formula for the secondary feature value VII is A1 The bounding rectangle R is calculated from the length of each side of A1 Area of ​​ / Circumscribed rectangle R B1The bounding rectangle R is calculated from the length of each side of B1 The final secondary feature value VII is calculated by the ratio (area of ​​the circumscribing rectangle R A1 Area of ​​ / Circumscribed rectangle R B1 (area of ​​the surface) and is a dimensionless quantity.

[0085] In addition, when the welding object 90 is a thin plate and the object to be judged or evaluated is classified as "burn-through," "sound weld," or "insufficient back weld," the secondary feature may be determined based on the welding image captured by the first camera 10a as follows:

[0086] For example, the primary feature used to identify secondary feature VIII as another secondary feature is calculated from the following four feature points obtained based on the welding image captured by the first camera 10a. That is, the primary feature is the length between the left end point of the weld pool region and the right end point of the weld pool region, which corresponds to the left-to-right width of the weld pool, and the length between the top end point of the weld pool region and the bottom end point of the weld pool region, which corresponds to the top-to-bottom width of the weld pool. In this case, the calculation formula for secondary feature VIII is a formula for calculating a ratio expressed as (top-to-bottom width of the weld pool / bottom-to-bottom width of the weld pool). The finally calculated secondary feature VIII is (top-to-bottom width of the weld pool / bottom-to-bottom width of the weld pool), which is a dimensionless quantity.

[0087] Furthermore, the primary feature used to identify secondary feature IX as another secondary feature is calculated from the following four feature points obtained based on the welding image captured by the first camera 10a. That is, the primary feature is the length between the upper end point of the weld pool area and the left end point of the weld pool area, which corresponds to the upper left width of the weld pool, and the length between the upper end point of the weld pool area and the lower end point of the weld pool area, which corresponds to the vertical width of the weld pool. In this case, the calculation formula for secondary feature IX is a formula for calculating a ratio expressed as (vertical width of the weld pool / upper left width of the weld pool). The finally calculated secondary feature IX is (vertical width of the weld pool / upper left width of the weld pool), which is a dimensionless quantity.

[0088] Furthermore, the primary feature used to identify secondary feature X as another secondary feature is calculated from the following four feature points obtained based on the welding image captured by the first camera 10a. That is, the primary feature is the length between the left end point of the weld pool area and the right end point of the weld pool area, which corresponds to the left-right width of the weld pool, and the length between the right end point of the weld pool area and the bottom end point of the weld pool area, which corresponds to the bottom-right width of the weld pool. In this case, the calculation formula for secondary feature X is a formula for calculating a ratio expressed as (bottom-right width of the weld pool / left-right width of the weld pool). The finally calculated secondary feature X is (bottom-right width of the weld pool / left-right width of the weld pool), which is a dimensionless quantity.

[0089] Furthermore, the primary feature used to identify the secondary feature XI as another secondary feature is calculated from the following four feature points obtained based on the welding image captured by the first camera 10a. That is, the primary feature is the length between the left end point of the weld pool region and the top end point of the weld pool region, which corresponds to the upper left width of the weld pool, and the length between the right end point of the weld pool region and the bottom end point of the weld pool region, which corresponds to the lower right width of the weld pool. In this case, the calculation formula for the secondary feature XI is a formula for calculating a ratio expressed as (lower right width of the weld pool / upper left width of the weld pool). The finally calculated secondary feature XI is (lower right width of the weld pool / upper left width of the weld pool), which is a dimensionless quantity.

[0090] 17A and 17B are diagrams relating to a fifth example of feature points and their extraction conditions, which are extracted from a welding image captured by the third camera 10c and relate to a case where the welding operation target 90 is a thick plate. When the welding operation target 90 is a thick plate and the object to be judged and evaluated is the presence or absence of incomplete fusion in a welding operation with classification, the secondary feature amount XII can be identified based on the feature points and their extraction conditions shown in FIGS.

[0091] 17A is a diagram showing a welding image on which a plurality of feature points are plotted. The feature points according to the fifth example are, for example, feature points P 1B , feature point P 2A , feature point P 2B and feature point P3, for a total of four. 1Bis the lower end point of the molten pool region. 2A is the left end point of the molten pool area. 2B is the right end point of the molten pool region. Feature point P3 is the center of gravity of the arc region.

[0092] 17B is a graph for explaining the extraction conditions for each feature point extracted based on each mask of the arc region and the molten pool region. Each mask of the arc region and the molten pool region in FIG. 17B is extracted based on the welding image shown in FIG. 17A. Regarding the circumscribing rectangle of the arc region, the minimum value in the X direction is set as X A1 and the maximum value in the X direction is X A2 and the minimum value in the Y direction is Y A1 and the maximum value in the Y direction is Y A2 The feature points in the fifth example can basically be extracted by applying the extraction conditions for feature points in the third example described with reference to FIG. 8B. Meanwhile, feature point P3 is extracted as the center of gravity of the circumscribing rectangle of the arc region.

[0093] In this case, the primary feature values ​​used to identify the secondary feature value XII are the feature points P3 and P 1B The fifth length L5 between the characteristic point P 2A and feature point P 2B The fifth length L5 corresponds to the length between the center of gravity of the arc region and the front end point of the weld pool region. The sixth length L6 corresponds to the width of the weld pool. The calculation formula for the secondary feature quantity XII is a formula for calculating the ratio expressed as (fifth length L5 / sixth length L6). The finally calculated secondary feature quantity XII is expressed as (fifth length L5 / sixth length L6) (length between the center of gravity of the arc region and the front end point of the weld pool region / width of the weld pool), and is a dimensionless quantity.

[0094] Next, following the secondary feature identification step S105, the control and calculation unit 11 executes a reference information acquisition step S106. In the reference information acquisition step S106, the control and calculation unit 11 queries the database storage unit 16 to acquire reference information that will serve as the basis for judgment and evaluation in the subsequent judgment and evaluation step S107. The reference information refers to information selected for each secondary feature, such as welding condition numerical values, quality judgment based on quantification, or relational expressions that lead to the quantification of skills. The reference information is continuously stored in various reference information databases in the database storage unit 16, which are classified by secondary feature. Below, specific reference information and the databases that the control and calculation unit 11 queries to acquire the reference information will be exemplified for each secondary feature.

[0095] When the secondary feature quantity according to the judgment / evaluation target is secondary feature quantity I, the reference information is a threshold value for the presence or absence of poor fusion for secondary feature quantity I. Similarly, when the secondary feature quantity according to the judgment / evaluation target is secondary feature quantity II, the reference information is a threshold value for the presence or absence of poor fusion for secondary feature quantity II. The reference information regarding secondary feature quantity I or secondary feature quantity II is stored in a first reference information database related to welding quality judgment or skill quantification.

[0096] Furthermore, when the secondary feature quantity according to the object of judgment / evaluation is secondary feature quantity III, the reference information is the correlation between secondary feature quantity III and heat input. On the other hand, when the secondary feature quantity according to the object of judgment / evaluation is secondary feature quantity IV, the reference information is the correlation between secondary feature quantity IV and welding speed. The reference information regarding secondary feature quantity III or secondary feature quantity IV is stored in a second reference information database regarding the quantification of welding conditions.

[0097] Furthermore, when the secondary feature quantity corresponding to the object of judgment / evaluation is secondary feature quantity V, the reference information is the optimal value that results in an appropriate weld pool shape for secondary feature quantity V. The weld pool shape corresponds to the back wave formation characteristics. Similarly, when the secondary feature quantity corresponding to the object of judgment / evaluation is any of secondary feature quantities VI to XI, the reference information is the optimal value that results in an appropriate weld pool shape for that secondary feature quantity. The reference information for each secondary feature quantity, from secondary feature quantity V to secondary feature quantity XI, is stored in a third reference information database related to back wave formation.

[0098] Furthermore, when the secondary feature according to the object to be judged or evaluated is secondary feature XII, the reference information is a threshold value for determining whether or not there is poor fusion for each number of passes for secondary feature XII. The reference information regarding secondary feature XII is stored in the first reference information database, similar to the reference information regarding secondary feature I or secondary feature II.

[0099] Next, the control and calculation unit 11 executes the judgment and evaluation step S107. In the judgment and evaluation step S107, the control and calculation unit 11 judges or evaluates the welding quality, skill, etc. in real time from the secondary feature quantities quantified in the secondary feature quantity identification step S105, using the reference information acquired in the reference information acquisition step S106 as a reference. The control and calculation unit 11 may derive a judgment and evaluation result based on any one of the multiple secondary feature quantities exemplified above, or may derive multiple judgment and evaluation results based on multiple secondary feature quantities. In this embodiment, the welding to be judged or evaluated is welding performed by an automatic welding machine or manual welding performed by a worker, including semi-automatic welding. Therefore, below, examples of judgment and evaluation for each secondary feature quantity will be described in relation to the welding to be judged or evaluated and the object of evaluation or evaluation.

[0100] Regarding the judgment or evaluation based on the secondary feature quantity I, in welding by an automatic welding machine, the presence or absence of incomplete fusion regarding the welding quality when the welding object 90 is a medium plate can be judged. On the other hand, in manual welding, the presence or absence of incomplete fusion regarding the skill can be evaluated when the welding object 90 is a medium plate.

[0101] 10B is a graph showing the secondary feature value I versus heat input (J / cm). In the graph, plots indicated by solid circles correspond to the secondary feature value I when it is determined that there is no incomplete fusion in the weld, i.e., that there is no defect. On the other hand, plots indicated by open circles correspond to the secondary feature value I when it is determined that there is incomplete fusion in the weld.

[0102] Regarding the relationship between the secondary feature value I and the object of judgment / evaluation, when the secondary feature value I is small, the shape of the weld pool is close to a straight line and stable. On the other hand, when the secondary feature value I is large, the leading edge point of the weld pool region and the trailing edge point of the weld pool region are offset in the Y direction, resulting in a meandering weld pool and an unstable weld pool. Therefore, when the value of the secondary feature value I is equal to or greater than a threshold value, which is reference information regarding the secondary feature value I, the control / calculation unit 11 judges / evaluates that there is a high possibility of incomplete fusion. In general welding operations, when the heat input is insufficient, welding is performed under low heat input conditions, and the weld pool is likely to have a meandering shape. In contrast, judgment or evaluation based on the secondary feature value I allows the presence or absence of incomplete fusion to be judged or evaluated regardless of the amount of heat input.

[0103] In the judgment or evaluation based on the secondary feature value II, the presence or absence of incomplete fusion can be judged or evaluated in both welding by an automatic welding machine and manual welding, in the same way as in the case based on the secondary feature value I.

[0104] 11B is a graph showing secondary feature quantity II versus heat input (J / cm). In the graph, plots indicated by solid circles correspond to secondary feature quantity II when it is determined that there is no incomplete fusion in the weld, i.e., that there is no defect. On the other hand, plots indicated by open circles correspond to secondary feature quantity II when it is determined that there is incomplete fusion in the weld.

[0105] Regarding the relationship between the secondary feature quantity II and the object of judgment / evaluation, when the secondary feature quantity II is small, the movement of the molten pool does not follow the movement of the wire 82, resulting in an unstable shape of the molten pool. On the other hand, when the secondary feature quantity II is large, the front end point of the molten pool region is located directly below the wire 82, resulting in a stable shape of the molten pool. Therefore, when the value of the secondary feature quantity II is equal to or greater than a threshold value, which is reference information regarding the secondary feature quantity II, the control / calculation unit 11 judges / evaluates that there is a high possibility of incomplete fusion. In general welding operations, if the rod operation is inappropriate, welding is performed under low heat input conditions, making it difficult for the movement of the molten pool to follow the movement of the wire 82. In contrast, judgment or evaluation based on the secondary feature quantity II allows the presence or absence of incomplete fusion to be judged or evaluated regardless of the amount of heat input.

[0106] Regarding the determination or evaluation based on the secondary feature quantity III, in welding by an automatic welding machine, the influence on the material regarding the welding quality when the welding target 90 is a medium plate can be determined. On the other hand, in manual welding, the error from the allowable range of the heat input regarding the skill when the welding target 90 is a medium plate can be evaluated.

[0107] 12B is a graph showing secondary feature III versus heat input (J / cm). In the graph, a predetermined allowable range of heat input is shown as an area surrounded by a dashed line.

[0108] As a relationship between the secondary feature quantity III and the object to be judged / evaluated, when the secondary feature quantity III is small, the heat input is insufficient, whereas when the secondary feature quantity III is large, the heat input is excessive. Therefore, the control calculation unit 11 estimates the heat input by applying the secondary feature quantity III calculated based on the welding image captured during the welding operation to the correlation, which is reference information related to the secondary feature quantity III, and judges / evaluates whether the estimated heat input is within an allowable range.

[0109] Here, the secondary feature value III is based on the welding image captured by the second camera 10b. The second camera 10b may be mounted on the worker himself. However, the secondary feature value III is based on the circumscribing rectangle R related to the dimensions of the molten pool.B is the area of ​​the molten pool and is not a dimensionless quantity. Therefore, for example, if the second camera 10b is mounted on the worker himself, when the distance between the worker and the molten part changes, the dimensions of the molten pool at the angle of view of the second camera 10b also change, which may make it impossible to accurately estimate the amount of heat input. Therefore, the control and calculation unit 11 has a separately installed IMU (Inertial Measurement Unit) sensor measure the distance between the worker and the weld part during welding, and calculates the circumscribing rectangle R in accordance with the distance measured by the IMU sensor. B The area may be converted into a value that can be judged and evaluated.

[0110] Regarding the determination or evaluation based on the secondary feature value IV, in welding by an automatic welding machine, the influence on the material regarding the welding quality when the welding target 90 is a medium plate can be determined. On the other hand, in manual welding, the error from the allowable range of the welding speed regarding the skill when the welding target 90 is a medium plate can be evaluated.

[0111] 13B and 13C are graphs showing the secondary feature value IV versus the welding speed (cm / min). The secondary feature value IV in FIG. 13B was obtained under first standard conditions where the welding current was 160 A and the welding voltage was 21.9 V. The secondary feature value IV in FIG. 13C was obtained under second standard conditions where the welding current was 230 A and the welding voltage was 26.0 V. In each graph, a predetermined allowable range for the welding speed is indicated by an area surrounded by a dashed line.

[0112] As for the relationship between the secondary feature value IV and the object of judgment / evaluation, under standard conditions of the same current and voltage, when the secondary feature value IV is small, the welding speed is fast, whereas when the secondary feature value IV is large, the welding speed is slow. Therefore, the control / calculation unit 11 estimates the welding speed by applying the secondary feature value IV calculated based on the welding image captured during the welding operation to the correlation, which is standard information related to the secondary feature value IV, and judges / evaluates whether the estimated welding speed is within the allowable range. Under the same current and voltage conditions, when the welding speed is fast, the length of the molten pool tends to be long, and therefore the secondary feature value IV becomes small. Therefore, in judgment or evaluation based on the secondary feature value IV, the welding speed can be estimated based on the welding image.

[0113] FIG. 18 is a table showing the results of the evaluation based on secondary feature quantities V through VII when the welding target 90 is a thin plate and the evaluation target is a back-beam formation characteristic. The values ​​of each secondary feature quantity in the table are obtained from 11 welding runs, each numbered for evaluation. In other words, a total of three secondary feature quantities, secondary feature quantities V through VII, are identified for each welding run. The welding current and welding speed for each welding run are also shown in the table. The evaluation target is visually classified into three evaluation patterns: "burn-through," "sound weld," or "insufficient back-beam" after welding. According to this classification method, if the evaluation target is classified as either "burn-through" or "insufficient back-beam," it is deemed to be an unsound weld.

[0114] 18, it is considered that the magnitude of each value of secondary feature quantity V to secondary feature quantity VII is related to the tendency of the pass / fail of the object to be judged / evaluated. Therefore, the control calculation unit 11 can refer to the tendency of these secondary feature quantities relative to the object to be judged / evaluated, and perform judgment or evaluation based on secondary feature quantities V to secondary feature quantity VII as follows.

[0115] Regarding the judgment or evaluation based on secondary feature quantities V to VII, in welding by an automatic welding machine, it can be judged whether the welding quality when welding object 90 is a thin plate falls into one of the above three judgment patterns. On the other hand, in manual welding, it can be evaluated whether the skill when welding object 90 is a thin plate falls into one of the above three judgment patterns.

[0116] Regarding the relationship between the secondary feature value V and the object of judgment / evaluation, when the secondary feature value V is small, the length of the lower part of the groove of the molten pool, corresponding to the second length L2 in FIG. 14, becomes long, and the state after welding is likely to be burn-through. On the other hand, when the secondary feature value V is large, the length of the lower part of the groove of the molten pool becomes short, and the back ribs formed after welding are likely to be insufficient. Therefore, the control / calculation unit 11 judges / evaluates that the welding is sounder the closer the value of the secondary feature value V is to the optimal value, which is the reference information for the secondary feature value V. Here, the optimal value is, for example, 1.3.

[0117] Furthermore, in terms of the relationship between the secondary feature value VI and the object of judgment / evaluation, when the secondary feature value VI is small, the width of the weld pool corresponding to the third length L3 in FIG. 15 becomes narrow, making the state after welding more likely to be burn-through. On the other hand, when the secondary feature value VI is large, the width of the weld pool becomes wide, making the backside ribs formed after welding more likely to be insufficient. Therefore, the control / calculation unit 11 judges / evaluates the quality of the weld as the value of the secondary feature value VI approaches the optimal value, which is the reference information for the secondary feature value VI. Here, the optimal value is, for example, 2.5.

[0118] Furthermore, as a relationship between the secondary feature value VII and the object of judgment and evaluation, when the secondary feature value VII is small, the circumscribing rectangle R in FIG. 16B based on the welding image taken from the front is A2 On the other hand, when the secondary feature value VII is large, the circumscribing rectangle R A2 Therefore, the control and calculation unit 11 determines and evaluates that the welding is sound when the value of the secondary characteristic quantity VI is closer to the optimal value, which is the reference information regarding the secondary characteristic quantity VI.

[0119] The above-described judgment or evaluation based on secondary feature quantities V to VII can also be applied to judgment or evaluation based on secondary feature quantities VIII to XI as secondary feature quantities identified based on the welding image captured by first camera 10a. In this case, too, in welding using an automatic welding machine, it can be determined whether the welding quality when welding object 90 is a thin plate falls into one of the above three judgment patterns. On the other hand, in manual welding, it can be evaluated whether the skill when welding object 90 is a thin plate falls into one of the above three judgment patterns.

[0120] The relationship between the secondary feature value VIII and the object of judgment / evaluation is that when the secondary feature value VIII is small, the lateral width of the weld pool becomes narrow, making the welded state more likely to be burn-through. On the other hand, when the secondary feature value VIII is large, the lateral width of the weld pool becomes wide, making the welded state more likely to be insufficient. Therefore, the control / calculation unit 11 judges / evaluates the weld as being sounder the closer the value of the secondary feature value VIII is to the optimal value, which is the reference information for the secondary feature value VIII. Here, the optimal value is, for example, 0.8.

[0121] Furthermore, as for the relationship between the secondary feature value IX and the object of judgment / evaluation, when the secondary feature value IX is small, the width of the upper left of the weld pool becomes narrow, and the state after welding is likely to be burn-through. On the other hand, when the secondary feature value IX is large, the width of the upper left of the weld pool becomes wide, and the backside ribs formed after welding are likely to be insufficient. Therefore, the control / calculation unit 11 judges / evaluates that the welding is sound the closer the value of the secondary feature value IX is to the optimal value, which is the reference information for the secondary feature value IX. Here, the optimal value is, for example, 0.9.

[0122] Furthermore, as for the relationship between the secondary feature quantity X and the object of judgment / evaluation, when the secondary feature quantity X is small, the lateral width of the weld pool becomes narrow, making the state after welding more likely to be burn-through. On the other hand, when the secondary feature quantity X is large, the lateral width of the weld pool becomes wide, making the formation of backside ribs after welding more likely to be insufficient. Therefore, the control / calculation unit 11 judges / evaluates that the welding is sounder the closer the value of the secondary feature quantity X is to the optimal value, which is the reference information regarding the secondary feature quantity X. Here, the optimal value is, for example, 0.62.

[0123] Furthermore, regarding the relationship between the secondary feature value XI and the object of judgment / evaluation, when the secondary feature value XI is small, the upper left width of the weld pool becomes narrow, making the state after welding more likely to be burn-through. On the other hand, when the secondary feature value XI is large, the upper left width of the weld pool becomes wide, making the backside ribs formed after welding more likely to be insufficient. Therefore, the control / calculation unit 11 judges / evaluates the welding to be sounder the closer the value of the secondary feature value XI is to the optimal value, which is the reference information for the secondary feature value XI. Here, the optimal value is, for example, 1.2.

[0124] FIG. 19 is a table showing the results of judgment and evaluation based on the secondary feature XII when the welding target 90 is a thick plate. When welding thick plates, each layer is welded in multiple passes, a process known as distribution. Therefore, even under the same welding conditions, it is expected that incomplete fusion as a defect may or may not occur. Therefore, in judgment or evaluation based on the secondary feature XII, attention is paid to left-right asymmetry in addition to the welding phenomenon. FIG. 19 shows the presence or absence of defects and the value of the secondary feature XII identified in the welding process for each pass. However, values ​​for passes "1" through "3" are excluded from the table because there is no distribution for each pass. The presence or absence of defects was visually judged for each pass.

[0125] According to the judgment / evaluation results shown in Fig. 19, the value of the secondary feature XII in a pass when it is judged that there is a defect varies greatly from the value in a pass when it is judged that there is no defect. In other words, the magnitude of the value of the secondary feature XII is considered to be related to the tendency of the pass / fail of the judgment / evaluation object. Therefore, the control / calculation unit 11 can refer to the tendency of the secondary feature XII for the judgment / evaluation object and perform judgment or evaluation based on the secondary feature XII.

[0126] Regarding the determination or evaluation based on the secondary feature XII, in welding by an automatic welding machine, the presence or absence of incomplete fusion regarding the welding quality when the welding object 90 is a thick plate can be determined. On the other hand, in manual welding, the presence or absence of incomplete fusion regarding the skill can be evaluated when the welding object 90 is a thick plate.

[0127] The relationship between the secondary feature quantity XII and the object of judgment / evaluation is that when the secondary feature quantity XII is small, the arc is downward and stable, and it is considered that heat is being appropriately input throughout the entire weld pool. On the other hand, when the secondary feature quantity XII is large, the arc is deflecting significantly toward the groove wall, and it is considered that heat is not being input to the groove formed by the previous pass. Therefore, when the value of the secondary feature quantity XII is equal to or greater than a threshold value, which is the reference information regarding the secondary feature quantity XII, the control / calculation unit 11 judges / evaluates that there is a high possibility of insufficient fusion occurring.

[0128] Next, the control calculation unit 11 ends the welding (end welding S108), and then ends the execution of the welding execution determination step.

[0129] Next, the effects of the welding construction judgment method and welding construction judgment device 1 according to this embodiment will be described.

[0130] First, the welding procedure determination method according to this embodiment is a method for determining whether or not the molten pool H M The welding execution judgment method includes a step of photographing a welded portion including the welding image I obtained by photographing the welded portion (welding image input step S200). P Based on Arc H A or molten pool H MThe welding performance evaluation method further includes a step of identifying a primary feature value relating to at least one of the shapes (primary feature value identification step S104). The welding performance evaluation method further includes a step of identifying a secondary feature value as a dimensionless quantity from a calculation formula using the primary feature value as a variable (secondary feature value identification step S105). The welding performance evaluation method further includes a step of judging the welding quality or evaluating the skill of the welding worker based on the secondary feature value (judging / evaluating step S107).

[0131] On the other hand, the welding construction judgment device 1 according to this embodiment includes an imaging device 10 that captures an image of a welded portion including a molten pool during welding. A or molten pool H M The welding construction judgment device 1 further includes a storage unit 12 for storing a calculation formula for a secondary feature quantity as a dimensionless quantity, with a primary feature quantity relating to at least one of the shapes of the welding image I acquired from the imaging device 10 as a variable. P and a control calculation unit 11 that determines a primary feature based on the primary feature and a calculation formula acquired from a storage unit 12. The control calculation unit 11 further determines the welding quality or evaluates the skill of a welding worker based on the secondary feature.

[0132] In the welding construction judgment method and welding construction judgment device 1 according to this embodiment, when judging the welding quality or evaluating the skill of a welding worker, a welding image I P Rather than directly referencing primary feature values ​​based on the welding quality, secondary feature values ​​that use the primary feature values ​​as variables are referenced. Furthermore, because secondary feature values ​​are quantified as dimensionless quantities, they are less susceptible to the influence of welding phenomena that can change for each welding operation. Therefore, for each welding operation, variation in judgment and evaluation results for the same welding quality or the same skill is less likely to occur, improving the accuracy of welding quality judgment or skill evaluation.

[0133] As described above, according to the present embodiment, it is possible to provide a welding execution judgment method and a welding execution judgment device 1 that improve the accuracy of judging welding quality or evaluating the skill of a welding worker.

[0134] When determining the welding quality of welding performed by an automatic welding machine such as welding machine 80, the welding quality is quantified using secondary features. Therefore, by directly reflecting the results of such welding quality determination in the operation conditions of the automatic welding machine, the automatic welding machine can perform adaptive control in real time to correct deviations from optimal values.

[0135] On the other hand, when evaluating the skill of a welding worker in manual welding, the skill is also quantified using secondary features. Therefore, the evaluation results of such skills can be more suitable as indicators for skill training or skill transfer.

[0136] In addition, the welding construction judgment method according to this embodiment is A Arc area A corresponding to C , or molten pool H M The corresponding weld pool area M P , welding image I P From mask image I M This step corresponds to the arc region extraction step S202 or the molten pool region extraction step S203. The primary feature amount is the arc region A C or molten pool area M P The feature points P in the above example are extracted based on the shape of 1A Multiple feature points corresponding to arc area A C The circumscribing rectangle R A , or molten pool area M P The circumscribing rectangle R B It may be identified from

[0137] According to this welding construction judgment method, a plurality of characteristic points, a circumscribing rectangle R A and circumscribed rectangle R B is the mask image I M Arc region A extracted as C or molten pool area M P Therefore, it can be advantageous to improve the accuracy regarding the position or shape, or to make it easier to select a desired feature point.

[0138] In addition, in the welding construction judgment method according to this embodiment, the molten pool region M P may be extracted by machine learning. The machine learning employed here is C Welding image I from the center of gravity P The end points of the molten pool may be predicted by learning and determining the correct end point positions of the molten pool from the brightness values ​​on multiple search lines of the molten pool that extend to the end of the image.

[0139] For example, if the weld pool region is extracted by focusing on the increase or decrease in brightness, it may not be possible to accurately extract the feature points due to the influence of the brightness of fumes generated during welding or the darkness of positions far from the arc. P When extracting feature points, machine learning is applied, which statistically considers the characteristics of the data, thereby improving the accuracy of the extracted feature points.

[0140] In the welding construction determination method according to this embodiment, one of the plurality of feature points is a mask image I M Arc H, extracted as a depression in A This may correspond to the tip point of the wire 82 that forms the

[0141] Mask Image I M The feature point corresponding to the tip point of the wire 82 extracted as the depression in the molten pool H is, for example, the feature point P3 illustrated in FIG. 11 and the like regarding the secondary feature quantity II. M Whether the movement of the wire 82 follows the movement of the molten pool H M This welding procedure evaluation method is suitable for a case where the welding procedure target 90 is a middle plate and the object of evaluation is the presence or absence of incomplete fusion related to the followability of the molten pool to the wire 82.

[0142] In the welding construction determination method according to the present embodiment, one of the plurality of characteristic points is the arc region A C It may correspond to the center of gravity of

[0143] Arc Region AC The feature point corresponding to the center of gravity of the secondary feature quantity XII is, for example, the feature point P3 illustrated in FIG. 17A etc. When welding a thick plate, each layer is generally divided into multiple passes. C Since the movement of the center of gravity is related to the swing width of the arc, when the arc swings significantly toward the groove wall, it can be assumed that heat is not being input to the groove formed by the previous pass. This welding procedure evaluation method can be suitable, for example, when the welding procedure object 90 is a thick plate and the object of evaluation is the presence or absence of insufficient fusion.

[0144] In the welding construction judgment method according to the present embodiment, the secondary feature amount may be set for each welding construction object 90, or for each item focused on in judging the welding quality or for each item focused on in evaluating the skill. Alternatively, the secondary feature amount may be set for each of a plurality of welding images I obtained by photographing the weld from different photographing positions and photographing directions. P It may be set for each

[0145] According to this welding construction judgment method, as shown in the above-mentioned secondary feature amounts I to XII, at least any of the welding construction object 90, the judgment / evaluation object, or the welding image I P A plurality of secondary feature amounts can be set depending on whether the image capturing device 10 that acquires the secondary feature amounts is selected. Then, a determination / evaluation result can be derived based on any one of the plurality of secondary feature amounts, or a plurality of determination / evaluation results can be derived in a composite manner based on the plurality of secondary feature amounts. In particular, by deriving a plurality of determination / evaluation results in a composite manner based on the plurality of secondary feature amounts, the reliability of the determination / evaluation results can be improved.

[0146] In the welding construction determination method according to the present embodiment, the primary feature value may be a line passing through two feature points, and the secondary feature value may be the slope of the line.

[0147] The primary feature amount and secondary feature amount in this case correspond to, for example, the combination related to secondary feature amount I shown in Figures 10A and 10B, or the combination related to secondary feature amount II shown in Figures 11A and 11B. As described above, this welding execution judgment method can be advantageous for judging or evaluating the presence or absence of poor fusion related to welding quality or skill when welding execution target 90 is a middle plate.

[0148] Furthermore, in the welding construction judgment method according to this embodiment, the primary feature value may be a line segment connecting two feature points, and the secondary feature value may be the ratio between the length of one line segment formed by different combinations of two feature points and the length of another line segment.

[0149] The primary feature amount and secondary feature amount in this case correspond to, for example, the combination of secondary feature amount IV shown in Figures 13A to 13C. As described above, when welding target 90 is a medium plate, this welding execution judgment method can be advantageous for judging the influence on the material regarding the welding quality in welding by an automatic welding machine, or for evaluating the error from the allowable range of the welding speed regarding the skill of the welding operator in manual welding.

[0150] Alternatively, the primary feature amount and secondary feature amount in this case correspond to, for example, the combination related to secondary feature amount V shown in Fig. 14 or the combination related to secondary feature amount VI shown in Fig. 15. As described above, this welding construction determination method can be advantageous for determining or evaluating whether the back-beam formation property is classified as "burn-through," "sound weld," or "insufficient back-beam" when welding construction object 90 is a thin plate.

[0151] Alternatively, the primary feature amount and secondary feature amount in this case correspond to, for example, the combination related to secondary feature amount XII shown in Figures 17A to 17B. As described above, this welding execution evaluation method can be advantageous for determining or evaluating the presence or absence of incomplete fusion related to welding quality or skill when welding execution object 90 is a thick plate.

[0152] In the welding construction determination method according to the present embodiment, the primary feature amount isC The circumscribing rectangle R A In this case, the secondary feature amount may be the length of each side of the welding image I captured from one photographing position and photographing direction. P Based on the bounding rectangle R A1 and welding image I taken from other shooting positions and directions P Based on the bounding rectangle R A2 It may be a ratio of the area of ​​the

[0153] The primary feature amount and secondary feature amount in this case correspond to, for example, the combination related to secondary feature amount VII in relation to Figures 16A and 16B. As described above, this welding procedure determination method can be advantageous for determining or evaluating whether the back-beam formation property is classified as "burn-through," "sound weld," or "insufficient back-beam" when welding procedure target 90 is a thin plate.

[0154] Furthermore, in the welding construction judgment method according to this embodiment, the welding quality or skill may be judged or evaluated based on standard information relating to the pass / fail of the judgment of welding quality or the evaluation of skill, which is predefined based on the numerical value of the secondary feature.

[0155] According to this welding construction evaluation method, the secondary feature values ​​identified in the welding construction are compared with reference information that is predefined based on the numerical values ​​of the secondary feature values, thereby making it possible to easily evaluate the welding quality or the skill.

[0156] The welding construction judgment device according to this embodiment may also include an input unit 13 for inputting the welding construction object 90 and the items to be focused on in judging the welding quality or the items to be focused on in evaluating the skill. There may be a plurality of photographing devices 10, each with a different photographing position and photographing direction. The control and calculation unit 11 captures the welding image I used to identify the primary feature amount. P The camera 10 for acquiring the welding quality information may be selected from a plurality of camera devices 10. In this case, the camera device 10 may be selected for each welding object 90 input via the input unit 13, or for each item to be focused on in determining the welding quality or for each item to be focused on in evaluating the skill.

[0157] According to this welding construction judgment device 1, the control and calculation unit 11 acquires a welding image I from at least one of a plurality of image capturing devices 10 each having a different image capturing position and image capturing direction. P Therefore, the control and calculation unit 11 acquires the welding image I captured by the appropriate image capturing device 10 in accordance with the secondary feature amount to be adopted. P can be used.

[0158] Although several embodiments have been described, the embodiments can be modified or varied based on the above disclosure. All components of the above embodiments and all features described in the claims may be individually extracted and combined, unless they contradict each other. [Explanation of symbols]

[0159] 1. Welding work judgment device 10 Imaging equipment 11 Control and calculation section 12 Storage section 13 Input section A C Arc Region H A arc H M molten pool I M Mask Image I P Welding Images L1 First length L2 Second length L3 Third length L4 Fourth length L5 Fifth length L6 6th length M P Weld pool area P1,P 1A ,P 1B ,P2,P 2A ,P 2B ,P3,P 3A ,P 3B ,P 4A ,P 4B Minutiae R A circumscribed rectangle R A1circumscribed rectangle R A2 circumscribed rectangle R B circumscribed rectangle

Claims

1. a step of photographing a weld including a molten pool during welding; identifying a primary feature value relating to the shape of at least one of the arc and the molten pool based on a welding image obtained by photographing the weld; specifying a secondary feature value as a dimensionless quantity from a calculation formula using the primary feature value as a variable; a step of determining welding quality or evaluating the skill of a welding worker based on the secondary feature amount; extracting an arc region corresponding to the arc or a molten pool region corresponding to the molten pool from the welding image as a mask image; and the primary feature amount is identified from a plurality of feature points, a circumscribing rectangle of the arc region, or a circumscribing rectangle of the weld pool region, which are extracted based on the shape of the arc region or the weld pool region; A welding construction judgment method in which the molten pool region is extracted using machine learning that predicts the molten pool endpoints by learning and determining the correct molten pool endpoint positions from the brightness values ​​on multiple search lines of the molten pool extending from the center of gravity of the arc region to the edge of the welding image.

2. The welding construction judgment method according to claim 1 , wherein one of the plurality of feature points corresponds to a tip point of a wire forming the arc, the tip point being extracted as a depression in the mask image.

3. The welding construction determination method according to claim 1 , wherein one of the plurality of characteristic points corresponds to a center of gravity of the arc region.

4. The welding construction judgment method according to any one of claims 1 to 3, wherein the secondary feature amount is set for each welding construction object, for each item focused on in judging the welding quality or for each item focused on in evaluating the skill, or for each of a plurality of welding images obtained by photographing the welded portion from different photographing positions and photographing directions.

5. the primary feature is a straight line passing through the two feature points, The welding construction judgment method according to claim 1, wherein the secondary feature amount is a slope of the straight line.

6. the primary feature is a line segment connecting two of the feature points, 4. The welding construction judgment method according to claim 1, wherein the secondary feature amount is a ratio between a length of one of the line segments formed by different combinations of two of the feature points and a length of another of the line segments.

7. the primary feature amount is the length of each side of the circumscribing rectangle of the arc region; The welding construction judgment method according to any one of claims 1 to 3, wherein the secondary feature is a ratio between an area of ​​the circumscribing rectangle based on the welding image photographed from one photographing position and photographing direction and an area of ​​the circumscribing rectangle based on the welding image photographed from another photographing position and photographing direction.

8. The welding execution judgment method according to any one of claims 1 to 7, wherein the welding quality or the skill is judged or evaluated based on reference information relating to whether the judgment of the welding quality or the evaluation of the skill is good or bad, which is specified in advance based on the numerical value of the secondary feature amount.

9. an imaging device for imaging the welded portion including the molten pool during welding; a storage unit that stores a calculation formula for a secondary feature value as a dimensionless quantity using a primary feature value relating to the shape of at least one of the arc and the molten pool as a variable; a control and calculation unit that identifies the primary feature amount based on the welding image acquired from the imaging device, identifies the secondary feature amount based on the primary feature amount and the calculation formula acquired from the storage unit, and judges the welding quality or evaluates the skill of a welding worker based on the secondary feature amount; an input unit for inputting a welding object and an item to be focused on in determining the welding quality or an item to be focused on in evaluating the skill; Equipped with The photographing device is provided in a plurality of positions and directions different from each other, The control and calculation unit selects, from the plurality of photographing devices, the photographing device that acquires the welding image used to identify the primary feature for each of the welding work objects, or for each of the items that are focused on in determining the welding quality or for each of the items that are focused on in evaluating the skill, which are input via the input unit.

Images