Welding condition setting method, welding condition setting program, and welding condition setting device

Abstract

To provide a welding condition setting method, a welding condition setting program, and a welding condition setting device that allow for setting welding conditions with a margin of safety in automated welding by robots. [Solution] The welding condition setting method according to the present invention is a welding condition setting method for setting welding conditions for joining members together, and includes: a precondition setting step of setting preconditions that include fixed values ​​relating to the members to be joined and a plurality of sets of welding condition parameters, each set consisting of a plurality of different parameter types; a weld shape prediction step of predicting the shape of the weld formed by welding according to the preconditions for each set of welding condition parameters; a determination step of determining whether the predicted weld shape of each set is good or bad; and a decision step of determining a set of welding condition parameters to be set as a welding condition from among the welding condition parameter sets that were determined to be good in the determination step.

Description

[Technical Field]

[0001] The present invention relates to a welding condition setting method, a welding condition setting program, and a welding condition setting apparatus. [Background technology]

[0002] Conventionally, arc welding is known as a method for joining metal components. Arc welding is a technique that uses the heat generated by applying a voltage to the components to be joined to create an electrical discharge phenomenon (arc discharge), thereby joining metal materials. Furthermore, a technique is known for setting the conditions for this arc welding by estimating the bead shape through simulation and setting the welding conditions based on the simulation results (see, for example, Patent Document 1). [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2008-200691 [Overview of the project] [Problems that the invention aims to solve]

[0004] Incidentally, in recent years, there has been a demand for the automation of arc welding using robots for joining metal components. However, since it is difficult for machines to correct for such disturbances, it is desirable to set welding conditions with a margin of safety. However, conventional technologies such as those described in Patent Document 1 did not allow for the setting of welding conditions with such a margin of safety.

[0005] The present invention has been made in view of these circumstances, and its purpose is to provide a welding condition setting method, a welding condition setting program, and a welding condition setting device that can set welding conditions with a margin of safety in automated welding by a robot. [Means for solving the problem]

[0006] To solve the above-mentioned problems and achieve the objective, a welding condition setting method according to one aspect of the present invention is a welding condition setting method for setting welding conditions for joining members together, comprising: a precondition setting step of setting preconditions including fixed values ​​relating to members to be joined and a plurality of sets of welding condition parameters, each set consisting of a plurality of different parameter types; a weld shape prediction step of predicting the shape of the weld formed by welding according to the preconditions for each set of welding condition parameters; a determination step of determining whether the predicted weld shape of each set is good or bad; and a decision step of determining a set of welding condition parameters to be set as welding conditions from among the welding condition parameter sets that were determined to be good in the determination step.

[0007] Furthermore, in a welding condition setting method according to one aspect of the present invention, the determination step includes a first parameter set selection step of extracting a welding condition parameter set that satisfies a first condition as a candidate from among the welding condition parameter sets that were judged to be good in the judgment step, and a second parameter set selection step of setting a welding condition set that satisfies a second condition different from the first condition from among the welding condition parameter sets selected in the first parameter set selection step as a welding condition.

[0008] Furthermore, in a welding condition setting method according to one aspect of the present invention, the first parameter set selection step extracts candidates for each of the welding condition parameter sets that were judged as good in the judgment step by assigning a predetermined weight to a score as the first condition, and the second parameter set selection step sets the welding condition with a score equal to or greater than a predetermined score from the scored candidate welding condition parameter sets as the second condition.

[0009] Further, in the welding condition setting method according to one aspect of the present invention, in the above invention, the determining step comprises: a region setting step of setting a region formed by the favorably determined welding condition parameter sets by extracting, as candidates, the welding condition parameter sets satisfying a first condition from among the welding condition parameter sets favorably determined in the determining step; and a determining step of determining a set of welding condition parameters within the region set in the region setting step as welding conditions.

[0010] Further, in the welding condition setting method according to one aspect of the present invention, in the above invention, the set of welding condition parameters serving as the welding conditions determined in the determining step is a set of welding condition parameters located at the midpoint or the centroid of the shape formed by the contour of the region set in the region setting step.

[0011] Further, in the welding condition setting method according to one aspect of the present invention, in the above invention, the number of parameter types is two, and the determining step sets, as the welding conditions, a set of parameters at which the centroid of the favorably determined region is located in a determination map showing determination results of parameter sets.

[0012] Further, in the welding condition setting method according to one aspect of the present invention, in the above invention, the number of parameter types is two, and in the orthogonal coordinate system in which a region is formed in the region setting step, a set of parameters that is inscribed in the region formed by favorable determination and located within a circle having the maximum area is set as the welding conditions.

[0013] Further, in the welding condition setting method according to one aspect of the present invention, in the above invention, the set of parameters set as welding conditions is a set of parameters located within a distance of 70% of the radius from the centroid of the circle having the maximum area.

[0014] Further, in the welding condition setting method according to one aspect of the present invention, in the above invention, the set of parameters set as welding conditions is a set of parameters at which the centroid of the circle having the maximum area is located.

[0015] Furthermore, in one aspect of the present invention, the welding condition setting method is characterized in that, in the above invention, there are three types of parameters, and in the region setting step, a set of parameters located inside a sphere that is inscribed in the region formed by the good judgment and has the largest volume in the orthogonal coordinate system in which the region is formed is set as the welding condition.

[0016] Furthermore, in one aspect of the present invention, the welding condition setting method is such that the set of parameters set as welding conditions in the above invention is a set of parameters located within 80% of the radius from the centroid of the sphere having the maximum volume.

[0017] Furthermore, in one aspect of the present invention, the welding condition setting method is such that the set of parameters set as welding conditions in the above invention is a set of parameters located at the centroid of the sphere having the maximum volume.

[0018] Furthermore, in one aspect of the present invention, the welding condition setting method is characterized in that, in the above invention, there are two types of parameters, and in the two-dimensional orthogonal coordinate system in which the region is formed in the region setting step, the welding condition is set to a set of parameters where the midpoint of the line segment connecting the first midpoint of the range of one parameter that has the widest range of good judgment for the other parameter and the second midpoint of the range of the other parameter that has the widest range of good judgment for the one parameter is located.

[0019] Furthermore, in one aspect of the present invention, the welding condition setting method is characterized in that, in the above invention, there are three parameter types, and in the area setting step, the set of parameters to which the centroid of the triangle connecting the centroids of the good judgment areas in each of the three two-dimensional orthogonal coordinate systems in which the area is formed is located is set as the welding condition.

[0020] Furthermore, in one aspect of the present invention, a welding condition setting method is provided in which, in the above invention, members are joined by the formation of multiple welds, the weld shape prediction step predicts the weld shape for each set of welding condition parameters for the formation of each weld, the determination step determines the quality of the weld for each predicted set of welding condition parameters for each weld, and the decision step sets the welding conditions for each weld.

[0021] Furthermore, a welding condition setting program according to one aspect of the present invention is a welding condition setting program that causes a computer to set welding conditions for joining members together, and causes the computer to execute the following steps: a precondition setting step that sets preconditions including fixed values ​​relating to the members to be joined and a plurality of sets of welding condition parameters, each set consisting of a plurality of different parameter types; a weld shape prediction step that predicts the shape of the weld formed by welding according to the preconditions for each set of welding condition parameters; a determination step that determines whether the welding of each predicted set of weld shapes is good or bad; and a decision step that determines a set of welding condition parameters to be set as welding conditions based on the good or bad determination of the weld shape in the determination step.

[0022] Furthermore, in one aspect of the present invention, the welding condition setting program includes, in the above invention, a determination step which includes a first parameter set selection step which extracts as a candidate welding condition set that satisfies a first condition from among the welding condition parameter sets that were judged as good in the judgment step, and a second parameter set selection step which sets as a welding condition a set of welding condition parameters that satisfies a second condition different from the first condition from among the welding condition parameter sets selected in the first parameter set selection step.

[0023] Furthermore, a welding condition setting device according to one aspect of the present invention is a welding condition setting device for setting welding conditions for joining members together, comprising: a precondition setting unit that sets preconditions including a fixed value relating to the members to be joined and a plurality of sets of welding condition parameters, each set consisting of a plurality of different parameter types; an analysis unit that predicts the shape of the weld formed by welding according to the preconditions for each set of welding condition parameters and determines whether the weld is good or bad for each predicted set of weld shapes; and a condition setting unit that determines a set of welding condition parameters to be set as welding conditions based on the goodness determination of the weld shape determined by the analysis unit.

[0024] Furthermore, in a welding condition setting device according to one aspect of the present invention, the condition setting unit performs a first parameter set selection by extracting and calculating as a candidate welding condition parameter set that satisfies a first condition from among the welding condition parameter sets that have been judged as good by the analysis unit, and sets as a welding condition a set of welding condition parameters that satisfies a second condition different from the first condition from among the welding condition parameter sets selected in the first parameter set selection step. [Effects of the Invention]

[0025] The welding condition setting method, welding condition setting program, and welding condition setting device according to the present invention have the effect of enabling the setting of welding conditions with a margin of error in automated welding by a robot. [Brief explanation of the drawing]

[0026] [Figure 1] Figure 1 is a block diagram showing a schematic configuration of a welding condition setting device according to one embodiment of the present invention. [Figure 2] Figure 2 is a schematic diagram illustrating the overview of arc welding. [Figure 3] Figure 3 is a flowchart showing the flow of the welding condition setting process according to one embodiment of the present invention. [Figure 4] Figure 4 illustrates an example of parameter types that can be set as preconditions. [Figure 5] Figure 5 is a diagram illustrating the shape of the welded joint after arc welding. [Figure 6] Figure 6 is a flowchart showing the flow of the method for predicting the shape of a weld joint by arc welding. [Figure 7] Figure 7 shows an example of a temperature image generated by thermography. [Figure 8] Figure 8 shows the temperature calculated from the infrared intensity at each position along the dashed line (A) shown in Figure 7. [Figure 9] Figure 9 is a flowchart showing the flow of setting welding conditions. [Figure 10] Figure 10 is a diagram illustrating the application of marks. [Figure 11] Figure 11 is a diagram (part 1) illustrating an example of domain configuration. [Figure 12A] Figure 12A is a diagram (part 2) illustrating an example of setting up a region. [Figure 12B] Figure 12B is a diagram (part 3) illustrating an example of setting up a region. [Figure 12C] Figure 12C is a diagram (part 4) illustrating an example of domain configuration. [Figure 13] Figure 13 is a diagram (part 1) illustrating another example of domain configuration. [Figure 14A] Figure 14A is a second diagram illustrating another example of domain configuration. [Figure 14B] Figure 14B is a third diagram illustrating another example of domain configuration. [Figure 14C] Figure 14C is a fourth diagram illustrating another example of domain configuration. [Figure 15] Figure 15 is a flowchart showing the flow of setting welding conditions using a modified example. [Figure 16A] Figure 16A is a diagram (part 1) illustrating the setting of welding conditions using a modified example. [Figure 16B]Figure 16B is a diagram (part 2) illustrating the setting of welding conditions using a modified example. [Figure 16C] Figure 16C is a diagram (part 3) illustrating the setting of welding conditions using a modified example. [Figure 16D] Figure 16D is a diagram (part 4) illustrating the setting of welding conditions using a modified example. [Figure 16E] Figure 16E is a diagram (part 5) illustrating the setting of welding conditions using a modified example. [Figure 16F] Figure 16F is a diagram (part 6) illustrating the setting of welding conditions using a modified example. [Figure 16G] Figure 16G is a diagram (part 7) illustrating the setting of welding conditions using a modified example. [Figure 16H] Figure 16H is a diagram (part 8) illustrating the setting of welding conditions using a modified example. [Figure 16I] Figure 16I is a diagram (part 9) illustrating the setting of welding conditions using a modified example. [Figure 17] Figure 17 is a diagram (part 1) illustrating another example of welding condition setting. [Figure 18] Figure 18 is a diagram (part 2) illustrating another example of welding condition setting. [Figure 19] Figure 19 is a diagram illustrating the relationship between welding quality evaluation items and welding condition parameters. [Modes for carrying out the invention]

[0027] Hereinafter, one embodiment of the present invention will be described with reference to the drawings. In all the drawings of the following embodiment, the same or corresponding parts will be denoted by the same reference numerals. Furthermore, the present invention is not limited to the embodiment described below.

[0028] (Embodiment) Figure 1 is a block diagram illustrating the schematic configuration of a welding condition setting device according to one embodiment of the present invention. As shown in Figure 1, the welding condition setting device 10 may read information from an external server. Here, data input and output of the welding condition setting device 10 can be performed via network communication or contactless communication such as Bluetooth®. It is also possible to move data via a USB (Universal Serial Bus) memory or a disk recording medium such as a CD (Compact Disc), DVD (Digital Versatile Disc), or BD (Blu-ray® Disc). The network is configured by appropriately combining wired communication and wireless communication, and consists of one or more combinations such as a dedicated line, a public communication network such as the Internet, such as a LAN (Local Area Network), WAN (Wide Area Network), a telephone communication network such as a mobile phone or public line, or a VPN (Virtual Private Network).

[0029] The welding condition setting device 10 comprises a communication unit 11, an input / output unit 12, an analysis unit 13, a condition setting unit 14, a control unit 15, and a storage unit 16.

[0030] The communication unit 11 is, for example, a LAN interface board, a wired communication circuit for wired communication, or a wireless communication circuit for wireless communication. The LAN interface board, wired communication circuit, or wireless communication circuit is connected to a network. The communication unit 11, acting as both a transmitter and receiver, is connected to the network and communicates with external devices.

[0031] The input / output unit 12 can be composed of, for example, a touch panel display or a speaker microphone. The input / output unit 12 as an input means may include an interface that receives various information transmitted from an external server via the communication unit and outputs it to the control unit 15. The input / output unit 12 also includes a user interface such as a keyboard, input buttons, levers, a touch panel for manual input superimposed on a display such as an LCD, or a mouse. The input unit and output unit of the input / output unit 12 may be configured as separate components.

[0032] The analysis unit 13 estimates the shape of the weld obtained by arc welding under the set welding conditions, and determines the quality of the weld based on the shape of the weld.

[0033] The condition setting unit 14 sets welding conditions with a margin of error based on the welding quality judgment result from the analysis unit 13. The analysis unit 13 and the condition setting unit 14 are configured using processors such as CPUs, DSPs, and FPGAs.

[0034] The control unit 15 controls the operation of each part of the welding condition setting device 10. Specifically, the control unit 15 includes a processor having hardware such as a CPU, DSP, and FPGA, and a main memory unit such as RAM (Random Access Memory) and ROM (Read Only Memory) (none of which are shown).

[0035] The storage unit 16 is composed of a storage medium selected from volatile memory such as RAM, non-volatile memory such as ROM, EPROM (Erasable Programmable ROM), hard disk drive (HDD), and removable media. The removable media can be, for example, a USB memory stick, or a disk recording medium such as a CD, DVD, or BD. Alternatively, the storage unit 16 may be configured using a computer-readable recording medium such as an externally insertable memory card.

[0036] The memory unit 16 can store various programs such as an operating system (OS), knowledge extraction applications, various tables, and various databases for executing the operation of the welding condition setting device 10. These various programs can also be recorded on computer-readable recording media such as hard disks, flash memory, CD-ROMs, DVD-ROMs, and flexible disks and widely distributed.

[0037] Here, arc welding will be explained with reference to Figure 2. Figure 2 is a schematic diagram illustrating the overview of arc welding. First, as shown in Figure 2, arc welding is a method of joining objects 200 by generating an arc between the object to be welded 200 and a welding torch 210, and melting the object to be welded 200 with the heat generated by the arc. The part where the objects to be welded 200 are joined by melting is also called the welded joint 201. The welded joint 201 includes the part of the object to be welded 200 that has solidified after melting. The welded joint 201 also includes the heat-affected zone as defined in JIS Z 3001. The heat-affected zone is a part that has not melted due to the heat of welding, but whose structure, metallurgical properties, or mechanical properties have changed. The prediction method according to this disclosure may predict the shape of the welded joint 201 including at least a part of the heat-affected zone, or it may predict the shape of the welded joint 201 excluding the heat-affected zone.

[0038] The shape of the weld 201, i.e., the weld shape, is specified by the bead width, weld bead height, or penetration depth, etc. The weld shape can be controlled by the arc welding conditions. Conversely, the arc welding conditions must be selected in order to obtain the desired weld shape. The weld shape may include the cross-sectional shape of the weld 201. The weld shape may also include other shapes of the weld 201, such as the surface shape or toe shape of the weld 201.

[0039] Next, the welding condition setting process according to this embodiment will be described. Figure 3 is a flowchart showing the flow of the welding condition setting process according to one embodiment of the present invention. First, the control unit 15 sets the preconditions (step S101: precondition setting step). The control unit 15 sets preconditions input via the input / output unit 12, for example, or reads and sets preconditions stored in the storage unit 16 beforehand. In this step, the preconditions set include the welding parameters to be set, and parameters fixed as the welding target, such as the groove shape, the threshold for determining the quality of the welding, and the number of layers of the weld. In addition, the size of the member, etc., may be set as needed. In this embodiment, the control unit 15 performs the function of the precondition setting unit.

[0040] Figure 4 is a diagram illustrating an example of parameter types that can be set as preconditions. In arc welding, the angle θ of the groove (V-groove in Figure 4) formed by the members 101 and 102 to be joined, and the operating conditions of the welding torch 110 which can move (oscillate) in a zigzag motion in the direction of groove extension are set. The operating conditions of the welding torch 110 include the movement speed V of the welding torch 110. T And the movement width (welding operation width) W in the direction intersecting the stretching direction of the groove. T , the dwell time (end stop time) at the end of the movement width of the welding torch 110 T T These operating conditions can be used as welding parameters to be set. Furthermore, if the welded portion has a groove such as a bevel, as described above, the welding torch is moved not only in the direction in which the groove extends, but also in a direction intersecting the direction in which the groove extends, to perform the welding.

[0041] Arc welding is performed by butting the members 101 and 102 together and operating the welding torch 110 according to the operating conditions to join the members. Arc welding forms a welded joint 103, joining members 101 and 102. The above-described arc welding is repeated until a set number of layers is achieved.

[0042] Figure 5 is a diagram illustrating the shape of the weld after arc welding. Figure 5 shows an example of multi-layer welding where arc welding is repeated five times. In Figure 5, the welds are formed in the order of W1, W2, W3, W4, and W5, and the dashed line 104 shows the structural contour (groove shape) of the member before welding. As shown in Figure 5, arc welding melts and solidifies a part of the object to be joined, forming a weld over a wider area than the structural contour. Note that Figure 5 shows an example where there are five weld layers, and one weld (weld pass) is formed in each weld layer.

[0043] Here, arc welding is broadly classified into consumable electrode welding and non-consumable electrode welding. Some of the welding condition parameters to be managed differ between consumable electrode welding and non-consumable electrode welding. The following welding parameters, including those mentioned above, can be set as the welding parameters to be configured. (Common parameters) Target position, welding current, welding voltage, welding speed, oscillation speed (or oscillation period), oscillation end stop time, oscillation pitch, number of electrodes, distance between electrodes, DC / AC, polarity (for DC), frequency (for AC), balance (rise / fall interval: for AC), offset (for AC), phase difference (for multiple electrodes), presence or absence of pulse, pulse waveform, oscillation trajectory shape, torch forward / backward angle, torch tilt angle, oscillation angle, shielding gas type, shielding gas flow rate / temperature, base metal temperature, wire temperature The oscillation pitch is calculated from the welding speed, oscillation width, oscillation speed, and end stop time. The polarity is positive / negative. (Consumable electrode welding) Welding wire protrusion length, wire diameter, wire feeding speed, oscillation width, contact tip-base metal distance (Non-consumable electrode welding) Welding electrode protrusion length, electrode diameter, electrode tip shape (tip angle, flat section diameter), electrode material (ceritane, thoritan, ...), wire feeding speed, oscillation width, arc length In addition, in consumable electrode welding, the wire feeding speed and welding current are correlated, while in non-consumable electrode welding, they are set individually and independently. Furthermore, in consumable electrode welding, the oscillation range refers to the electrode targeting position, while in non-consumable electrode welding, the electrode targeting position and the wire targeting position are set independently.

[0044] Returning to Figure 3, the control unit 15 sets the welding pass number m to m=1 (step S102). The welding pass number m corresponds to a number assigned to welding passes that are formed at different timings. Here, the number of welding passes is set by the preconditions, and the maximum welding pass number is set to m. MAX Therefore, the welding pass number m MAX This represents the number of welding passes.

[0045] The control unit 15 then sets the shape of the welded joint immediately before. For example, the control unit 15 reads the shape of the welded joint in the previous welding pass number and sets it as the shape of the welded joint immediately before. In this case, the welded joint shape is set to the shape formed by the welding conditions in the previous welding pass number determined in step S106, which will be described later. If the welding pass number m is m=1, the control unit 15 sets a state (condition) where no welded joint has been formed and proceeds with the process.

[0046] Subsequently, the analysis unit 13 predicts the weld shape for welding pass number m (step S104: weld shape prediction step). In step S104, the analysis unit 13 predicts the weld shape when arc welding is performed according to the welding conditions, and calculates welding condition parameters from the predicted weld shape. At this time, the analysis unit 13 predicts the weld shape for multiple sets of conditions with different combinations of parameters for multiple specified welding parameter types.

[0047] Here, we will explain the prediction (simulation) of the weld shape by the analysis unit 13. The arc welding simulation includes heat conduction calculations in arc welding. The arc welding simulation estimates the weld shape by setting hypothetical values ​​for virtual parameters that represent arc heat input or arc pressure corresponding to the arc welding conditions and running the simulation. Each parameter is adjusted by repeatedly setting hypothetical values ​​and estimating so that the estimated weld shape approaches the actual weld shape.

[0048] For simulating arc welding, for example, a weld shape prediction model is used. The weld shape prediction model is configured to output a predicted result of the weld shape obtained by arc welding to which the arc welding conditions are applied, when the arc welding conditions are input.

[0049] The prediction model can, for example, use a finite element method (FEM) model. If the prediction model uses the finite element method, parameters determined according to the arc welding conditions are set in the boundary conditions of the finite element method. The prediction model may also use other prediction methods such as the finite difference method (FDM).

[0050] The boundary conditions, which are determined according to the arc welding conditions, include the arc heat input distribution. The arc heat input distribution is the distribution of arc heat input to each part of the surface of the object to be welded (e.g., object 200). The arc heat input is the distribution of arc heat input to each part of the surface of the object to be arc welded. The arc heat input is the amount of heat that enters the object to be welded from the arc.

[0051] During arc welding, a molten pool is formed on the surface of the workpiece. Heat entering the molten pool from the arc is transported into the pool by conduction or convection, melting even the unmelted solid parts inside the workpiece and expanding the melted area. Therefore, the temperature distribution on the surface of the molten pool during arc welding reflects the distribution of heat input from the arc, i.e., the arc heat input distribution. When the temperature distribution on the surface of the molten pool is set as a boundary condition in the prediction model of the weld shape, the heat transport phenomenon within the molten pool can be reproduced and the weld shape estimated by calculating an energy conservation equation that takes into account heat transport by conduction or convection within the molten pool.

[0052] Therefore, in the weld shape prediction method according to this embodiment, the surface temperature distribution of the object to be welded is set as the boundary condition of the weld shape prediction model. The surface temperature distribution of the object to be welded is measured during the execution of arc welding and may be saved in association with the arc welding conditions. In this case, the parameter set as the boundary condition can also be the arc heat input distribution, but by using the surface temperature distribution, the time required to obtain the weld shape prediction result using the weld shape prediction model is shortened compared to the arc heat input distribution, which takes time. By shortening the time required to obtain the weld shape prediction result, the time required to select the arc welding conditions is shortened.

[0053] As an example, the prediction model used in this embodiment is an energy conservation equation into which the surface temperature distribution of the object to be welded is input, and is expressed as equation (1) below.

number

[0054] The velocity u→ used in equation (1) is calculated by solving the following mass conservation equation (2) and momentum conservation equation (3). In equations (2) and (3), P represents pressure, μ represents viscosity, and F→ EX This represents external forces, including gravity, surface tension, or arc pressure.

[0055]

number

number

[0056] The range in which the surface temperature distribution of the workpiece to be welded is set as a boundary condition in the prediction model is preferably wider than the actual range affected by arc heat input in order to sufficiently incorporate the effect of arc heat input. For example, numerically, it is preferably a range with a radius of 2 mm or more. The mathematical formulas used in the above explanation are examples only and may be modified as needed.

[0057] Figure 6 is a flowchart showing the flow of the method for predicting the shape of a weld joint by arc welding. The analysis unit 13 acquires the welding conditions when the welding apparatus performs arc welding (step S201). The control unit 15 acquires the welding conditions based, for example, on information input via the input / output unit 12 or information acquired from an external device (welding apparatus). The welding conditions may include arc current or arc voltage. The welding conditions may include the speed at which the workpiece moves relative to the welding torch of the welding apparatus during arc welding.

[0058] The analysis unit 13 calculates the surface temperature distribution of the object to be welded during arc welding (step S202). The surface temperature distribution is estimated by the finite difference method using, for example, a temperature image generated by thermography, as shown in Figure 7, which is actually measured by a measuring device.

[0059] The temperature image in Figure 7 includes the molten area of ​​the workpiece. The molten area is the part of the workpiece that has melted due to the heat of arc welding. The molten area includes the arc heat input area. The arc heat input area is the part where the arc is directly inputting heat at the time the temperature image was taken. The temperature of the arc heat input area is the highest in the temperature image. In the temperature image in Figure 7, the arc heat input area corresponds to the area of ​​white pixels that indicate the highest temperature. The temperature of the part of the molten area other than the arc heat input area is lower than the temperature of the arc heat input area, but is higher than the ambient temperature outside the area being arc-welded. In the temperature image in Figure 7, the molten area corresponds to the area of ​​gray pixels that indicate a higher temperature than the surrounding area, and extends in the Y-axis direction.

[0060] Regarding the positional relationship between the temperature image and the welding apparatus in Figure 7, the welding torch 210 of the welding apparatus is located near the white pixels representing the arc heat input area in the temperature image. In the temperature image, the white pixels representing the arc heat input area are located in the positive Y-axis direction within the gray pixels representing the molten area, which means that arc welding is being performed while the object to be welded is moving in the negative Y-axis direction relative to the welding torch. Note that the temperature image in Figure 7 was taken when the thermographic camera of the measuring device was positioned in the negative Y-axis direction relative to the welding torch.

[0061] When the measuring device is a thermograph, the infrared intensity measurements obtained by photographing the molten area and the arc input area with a thermograph camera are affected by the emission of the arc. To remove the effect of arc emission from the infrared intensity measurements, the arc may be momentarily extinguished when photographing the molten area and the arc input area with the thermograph camera. By photographing the molten area and the arc input area with the thermograph camera while the arc is extinguished and no light is emitted, the effect of arc emission is removed from the infrared intensity measurements obtained by the thermograph.

[0062] Furthermore, it is preferable that the measuring device photographs the molten area and the arc heat input area after the arc welding has reached a quasi-steady state, that is, after the arc welding has been performed for a sufficient length of time.

[0063] When the measuring device is a thermography, a temperature image is generated by calculating the surface temperature from the measured infrared intensity based on the emissivity. The emissivity of the welding object differs between when the welding object is molten and when it is in a solid state. That is, the emissivity of the molten portion of the welding object is different from the emissivity of portions other than the molten portion. Therefore, the temperature image may be generated by setting different values for the emissivity of the molten portion and the emissivity of portions other than the molten portion. In this case, the emissivity of the molten portion may be set to a larger value than the emissivity of portions other than the molten portion. Specifically, when the welding object is a steel plate, the emissivity of the molten portion may be set to 0.1 to 0.5. The emissivity of portions other than the molten portion may be set to 0.4 to 1.0. The emissivity may be set to other values according to the physical properties of the welding object.

[0064] Here, in order to improve the accuracy of the surface temperature distribution in the temperature image, the surface temperature at a specific position of the welding object may be estimated. In this case, the temperature image is generated by correcting the overall surface temperature distribution so that the surface temperature at the specific position in the temperature image matches the estimated surface temperature. Specifically, in the welding object, a position where the surface temperature is the melting point of the welding object and a position where the surface temperature is the boiling point of the welding object are estimated. Further, a position where the surface temperature is the melting point of the welding object may be specified based on the distribution of infrared intensity. A closed curve connecting positions where the surface temperature is the melting point of the welding object corresponds to a boundary line surrounding the range of the molten portion.

[0065] The position where the surface temperature is the melting point of the welding object may be estimated based on the distribution of infrared intensity. As data corresponding to the infrared intensity distribution, the graph of FIG. 8 shows the result of calculating the temperature from the one-dimensional distribution of infrared intensity, that is, the infrared intensity at each position along the alternate long and short dash line (A) parallel to the X axis in the temperature image of FIG. 7. The horizontal axis of the graph in FIG. 8 represents the X coordinate of each position along the alternate long and short dash line (A). The vertical axis represents the surface temperature calculated from the infrared intensity at each position. Curve F including points plotted with solid circles (●) A represents the result of calculating the surface temperature with a uniform emissivity from the infrared intensity at each position. Curve F AThe surface temperature at each location is calculated using a uniform emissivity and is therefore proportional to the infrared intensity at each location.

[0066] curve F A The surface temperature distribution, i.e., the infrared intensity distribution, is shown by discontinuities P. D There exists. In this disclosure, a discontinuity is defined as a maximum point that appears while the infrared intensity is rising towards its peak. The discontinuity is not limited to the definition above, but may also be defined as a point where the rate of increase in infrared intensity with respect to the change in the X coordinate decreases sharply while the infrared intensity is rising towards its peak. Discontinuities in infrared intensity are caused by abrupt changes in emissivity due to changes in the state of the workpiece to be welded. Therefore, discontinuities in infrared intensity may be presumed to be the boundary between the part of the workpiece to be welded that is in a solid state and the part of the workpiece to be welded that is in a molten state, i.e., the molten part.

[0067] Also, curve F A The peak point in the surface temperature distribution, i.e., the infrared intensity distribution, can be presumed to be the point where the welded material is evaporating from the molten area. Therefore, the peak point in infrared intensity can be presumed to be the point where the surface temperature of the welded material is at its boiling point.

[0068] As described above, the curve F in Figure 8 A In this case, the location where the surface temperature of the object to be welded is at its melting point and the location where it is at its boiling point are estimated. In Figure 8, the curve F includes the points plotted as solid rectangles. B This is curve F A The surface temperature at the discontinuity point becomes the melting point of the material to be welded, and curve F A This graph is a transformation where the surface temperature at the peak point of the curve is converted to match the boiling point of the material being welded. Temperatures higher than the melting point and lower than the boiling point are appropriately transformed to maintain continuity. Note that curve F B A temperature image may be generated using the surface temperature distribution of the molten area and the arc heat input area.

[0069] In the temperature image of Figure 7, the dashed line (A) set to calculate the one-dimensional distribution of surface temperature, i.e., infrared intensity, in the X-axis direction, is set to pass through the point where the infrared intensity peaks. Alternatively, the two-dimensional distribution of infrared intensity may be calculated by calculating the one-dimensional distribution of infrared intensity in the X-axis direction for multiple different Y coordinates, or the maximum value in the two-dimensional distribution of infrared intensity may be associated with the boiling point of the material to be welded, or a boundary line where the infrared intensity becomes discontinuous in the two-dimensional distribution of infrared intensity may be identified, and the infrared intensity on the boundary line may be associated with the melting point of the material to be welded. If there is variation in the infrared intensity at each point on the boundary line, the measuring device may associate the minimum, maximum, or average value of the infrared intensity at each point on the boundary line with the melting point of the material to be welded.

[0070] In the example shown in Figure 8, the one-dimensional distribution of infrared intensity is calculated along the X-axis. However, the direction in which the one-dimensional distribution of infrared intensity is calculated is not limited to the X-axis; it may also be along the Y-axis or in any other direction.

[0071] As described above, the surface temperature distribution of the molten area is generated for the purpose of estimating the surface temperature distribution. Alternatively, the surface temperature distribution may be calculated from the infrared intensity distribution. Furthermore, although the prediction of the weld shape described above was explained using the surface temperature distribution, it may also be predicted using the pressure distribution during arc welding (arc pressure distribution). In this case, the arc pressure distribution is calculated, for example, using the luminance of the reflected light of the arc.

[0072] Returning to Figure 6, the analysis unit 13 inputs the surface temperature distribution of the molten area and the welding conditions of the arc welding, generated from the surface temperature distribution of the object to be welded, into the prediction model (step S203). The analysis unit 13 outputs the predicted result of the weld shape, i.e., the weld shape, from the prediction model (step S204). After executing the procedure in step S204, the analysis unit 13 terminates the execution of the flowchart in Figure 6.

[0073] The analysis unit 13 predicts the weld shape for each welding condition using the estimation process described above. From the predicted weld shape, the analysis unit 13 calculates parameters for determining the quality of the welding conditions.

[0074] Returning to Figure 3, the analysis unit 13 determines the quality of each combination of welding parameters based on the predicted weld shape for each welding condition (Step S105: Judgment Step). At this time, the analysis unit 13 calculates shape values ​​from the weld shape according to the specified welding parameters and determines the quality by comparing them with a threshold. For example, if welding parameters consisting of welding width and end stop time are specified as a set, the lateral penetration amount is calculated from the weld shape and this penetration amount is compared with a threshold. The lateral penetration amount is a value expressed by the difference between the structural contour and the weld shape, and may be the sum of the widths of both ends, the larger of the two, the smaller of the two, or the average value. In this case, if no good result is found, a notification process may be performed to prompt the user to change conditions such as parameters, or the initial parameters of the pre-set prerequisites may be changed.

[0075] After determining whether the welding is good or bad, the condition setting unit 14 determines the welding conditions for welding pass number m (step S106: determination step). Figure 9 is a flowchart showing the flow of setting welding conditions. The condition setting unit 14 inputs the judgment results for each set of welding parameters into the map (step S301). Here, in a map where cells representing pairs of two different types of parameters are arranged in a grid, the judgment results for the corresponding sets are input. Here, ○ is entered for a good judgment and × for a bad judgment.

[0076] Then, the condition setting unit 14 assigns the number n (n=1~n) to the cells that are judged as good. MAX The condition setting unit 14 then sets n=1 (step S303).

[0077] The condition setting unit 14 determines whether there are three consecutive ○ judgments for the squares surrounding the nth square, starting from the squares above, below, left, and right (step S304). If the condition setting unit 14 determines that there are three or more consecutive squares surrounding the target square in different directions (step S304: Yes), it proceeds to step S305. Conversely, if the condition setting unit 14 determines that there are not three or more consecutive squares surrounding the target square in different directions (step S304: No), it proceeds to step S306.

[0078] In step S305, the condition setting unit 14 assigns a solid mark (●) to a point in the Cartesian coordinate system corresponding to the combination of welding parameters for the nth mass. Furthermore, in step S306, the condition setting unit 14 assigns an open mark (〇) to a point in the Cartesian coordinate system corresponding to the combination of welding parameters for the nth mass.

[0079] Figure 10 is a diagram illustrating the marking process. The condition setting unit 14, as shown in the upper part of Figure 10, assigns a solid mark (●) to a point in the Cartesian coordinate system corresponding to the combination of welding parameters for the target mass (the central mass in Figure 10) if there are three or more consecutive masses surrounding the target mass that are connected in different directions. On the other hand, the condition setting unit 14, as shown in the lower part of Figure 10, assigns an open mark (〇) to a point in the Cartesian coordinate system corresponding to the combination of welding parameters for the target mass if there are three or more consecutive masses surrounding the target mass that are not connected in different directions.

[0080] After marking, the condition setting unit 14 increments the number n by 1 (step S307). Then, the condition setting unit 14 determines that the increased number n is n MAX It is determined whether it is greater than or less than (step S308). The condition setting unit 14 determines whether the number n after the increase is n MAXIf it is determined that the following is true (Step S308: No), the process returns to Step S304 and the above-described process is repeated. The condition setting unit 14 determines that the incremented number n is n MAX If it is determined to be greater than (Step S308: Yes), proceed to Step S309.

[0081] In step S309, the condition setting unit 14 sets a region where solid marks are connected by line segments. The condition setting unit 14 sets the region by connecting solid marks in a Cartesian coordinate system with line segments perpendicular or parallel to the coordinate axes.

[0082] Figures 11 and 12A-12C illustrate an example of region setting. The condition setting unit 14 sets a region, for example, by connecting the solid marks shown in Figure 11. Specifically, the condition setting unit 14 first extracts the points that have been judged as ○ (see Figure 12A). Then, the condition setting unit 14 connects the points located on the outer edge of the set of points that have solid marks with line segments (see Figure 12B). After that, the condition setting unit 14 sets the region R1 formed by the line segments (see Figure 12C).

[0083] In this case, when setting up regions, multiple regions that are independent of each other may be set. Figures 13 and 14A to 14C illustrate other examples of region setting. The condition setting unit 14 sets up multiple regions, for example, by connecting the solid marks shown in Figure 13 (see Figure 14). Specifically, the condition setting unit 14 extracts the points that have been judged as ○ (see Figure 14A), and connects the points located on the outer edge of each set of points that have solid marks with line segments (see Figure 14B). Then, the condition setting unit 14 sets regions R2 to R4 formed by the line segments (see Figure 14C). Note that in Figure 14C, region R2 has the largest area.

[0084] Returning to Figure 9, the condition setting unit 14 calculates the center or centroid of the region with the largest area (step S310). The condition setting unit 14 calculates the center or centroid for, for example, region R1 shown in Figure 12C and region R1 shown in Figure 14C. For example, centroid G1 is calculated in Figure 12C and centroid G2 in Figure 14C. In this case, weighting may be applied according to the parameter type, in which case the area of ​​the region may differ from that calculated from the size of the mass, and the center or centroid may also differ from that of the shape of the region on a mass basis.

[0085] After calculating the center or centroid, the condition setting unit 14 sets the welding conditions (step S311). The condition setting unit 14 sets a set of parameters corresponding to the mass where the center or centroid is located as the welding conditions (welding parameters). In the determination based on the set region shape, there is a possibility that the centroid may be calculated to be outside the region. In that case, parameters determined by other determination methods described later may be selected. Alternatively, the parameter set may be determined by considering both the parameters located at the center or centroid of the region and the parameters determined by the other determination methods.

[0086] This sets conditions that ensure the results remain within the acceptable range even if the two parameters deviate in any direction, thus setting the welding conditions with the greatest margin of error for welding pass number m.

[0087] Subsequently, the control unit 15 increments the welding pass number m by one (step S107). Then, the control unit 15 determines that the increased welding pass number m is m > m MAX The control unit 15 determines whether or not the welding pass number m is m > m MAX No, that is, m ≤ m MAX If it is determined that (Step S108: No), the process proceeds to Step S103, and the above-described process is repeated for the increased welding pass number m. In response, the control unit 15 determines that if the welding pass number m is m > m MAX If it is determined that this is the case (Step S108: Yes), proceed to Step S109.

[0088] In step S109, the control unit 15 outputs the welding conditions set for all welding pass numbers m. The output destinations here include the input / output unit 12 and the storage unit 16, and the output may be displayed on the display or stored in the storage unit 16.

[0089] In the embodiment described above, a map indicating the quality of welding conditions is created from the weld shape estimated from the arc welding conditions, and the centroid of the area judged as good in the map is set to the optimal welding conditions. According to this embodiment, among the conditions for good welding, the welding conditions are set to those that can guarantee good welding even with slight deviations in the conditions within the judgment space, so that welding conditions with a margin of error can be set in automatic welding.

[0090] In the embodiment described above, an example was explained in which the center or centroid is calculated from a set area and welding conditions are mechanically set based on this center or centroid. However, the set area may be displayed on a screen, and the user may manually set the welding conditions by referring to that area, or the welding conditions may be set using a trained model that has been trained to perform such manual selection (positional relationship to the area, etc.). In this case, the trained model may be, for example, a model that has been trained with parameters related to the shape of the area as explanatory variables and the center or centroid as the objective variable.

[0091] In the embodiments described above, an example was given in which the center or centroid position of the good judgment region in the map is set as the welding condition. However, the welding condition may be set by other methods, and this is not limited to this.

[0092] (modified version) Next, a modified example of this embodiment will be described with reference to Figures 15 and 16A to 16I. Note that the configuration of the welding condition setting device in this modified example is the same as that of the welding condition setting device 0 in the embodiment, and therefore its description will be omitted. In this modified example, the content of the welding condition setting process (step S106) differs from that of the embodiment described above. The following describes the processing content that differs from the embodiment.

[0093] Figure 15 is a flowchart showing the flow of setting welding conditions. The condition setting unit 14 inputs the judgment results for each set of welding parameters into the map in the same manner as in step S301 (step S401). For example, as shown in Figure 16A, a map is generated in which the judgment results are entered into each cell (set of parameters).

[0094] Then, the condition setting unit 14 scores each cell using the weighted nearest neighbor method (step S402). The condition setting unit 14 extracts welding condition parameter sets as candidates by assigning points based on predetermined weights. Here, regarding the judgment results of the cells surrounding the target cell, if cells lined up vertically and horizontally are judged as good, the number of cells × 1 (points) is assigned, and if cells lined up diagonally are judged as good, the number of cells × 0.5 (points) is assigned. For example, as shown in Figure 16B, a map is generated in which points are assigned to each cell (parameter set) according to the map shown in Figure 16A. Furthermore, scoring is not limited to the weighted nearest neighbor method described above; other filtering methods, such as the well-known Level-Set method, may also be used. Any known method that can quantify the judgment result in this way can be used.

[0095] After scoring each cell, the condition setting unit 14 extracts the maximum score (step S403). The condition setting unit 14 extracts the cell with the highest score.

[0096] Subsequently, the condition setting unit 14 determines whether the maximum score is zero or not (step S404). If the condition setting unit 14 determines that the maximum score is zero (step S404: Yes), it proceeds to step S409. Conversely, if the condition setting unit 14 determines that the maximum score is not zero (step S404: No), it proceeds to step S405.

[0097] In step S405, the condition setting unit 14 sets the square with the maximum score to ○. At this time, the condition setting unit 14 sets the squares with scores other than the maximum score to ×. For example, as shown in Figure 16C, according to the map shown in Figure 16B, the squares that have been awarded 6 points are set to ○, and the others are set to ×, and the map is updated.

[0098] Then, the condition setting unit 14 determines whether the updated map is the same as the map before the update (step S406). The condition setting unit 14 determines whether the positional relationship of the circles in the map before and after the update is the same. If the condition setting unit 14 determines that the map before and after the update is the same (step S406: No), it proceeds to step S407, replaces the map with the updated one, and then returns to step 402 to repeat the process described above. On the other hand, if the condition setting unit 14 determines that the map before and after the update is the same (step S406: Yes), it proceeds to step S408.

[0099] In step S408, the condition setting unit 14 performs an averaging process. The condition setting unit 14 calculates the average of the parameters corresponding to the cells with a circle rating. For example, if scoring is done for Figure 16C to obtain Figure 16D and the map is updated, and then the update is repeated as shown in Figures 16E to 16H, and there is no change in the map before and after the update as shown in Figures 16G and 16I, the average value of the welding parameters corresponding to the circles in this map is calculated.

[0100] Furthermore, in step S409, the condition setting unit 14 extracts the optimal parameters. In this modified example, if the maximum value obtained by scoring is zero, there will be a ○ cell where the surrounding cells are ×. If there is one such cell, the parameter corresponding to that cell is extracted as the optimal parameter. On the other hand, if there are multiple ○ cells where the maximum value is zero, for example, the weighting is changed and the scoring process is run again, or parameters are extracted based on pre-set conditions. In this case, for example, the conditions may include going back to the map before the update and selecting cells in groups with a large number of ○ cells as the cells with the optimal parameters, or, if the region is divided by the update, going back to the map before the update and calculating the center or centroid of the region in the map before the region was divided to select the cell with the optimal parameters.

[0101] After executing the process in step S408 or S409, the condition setting unit 14 sets the parameters calculated by the averaging process or the extracted parameters as welding conditions (step S311).

[0102] In the modified version described above, a map indicating the quality of welding conditions is created from the weld shape estimated from the arc welding conditions, and the optimal welding conditions are set according to the pattern of masses judged as good in the map. According to this modified version, similar to the embodiment, the welding conditions are set to conditions that can ensure good welding even with slight deviations in the conditions within the judgment space among the conditions that are considered to be good welding, so that welding conditions with a margin of error can be set in automatic welding.

[0103] In addition to the processes described above, for example, if the judgment results for each set are represented in a Cartesian coordinate system (n-dimensional space), welding conditions can be set based on the good judgment distribution in that coordinate system. Specifically, if there are two parameters and the judgment results are represented by a two-dimensional Cartesian coordinate system (two-dimensional space) representing each parameter, the combination of parameters within the circle that is inscribed in the region judged as good and has the largest area may be set as the welding conditions. Alternatively, the combination of distance parameters within a predetermined percentage range from the centroid (center) of such a circle with the largest area, or within a predetermined percentage range of the radius of the circle from the centroid (center), may be set as the welding conditions. In this case, it is preferable to set the combination of parameters that are within 70% of the radius from the centroid (center) of the circle as the welding conditions. Furthermore, even when there are three parameters and the judgment result is represented by a three-dimensional Cartesian coordinate system (three-dimensional space) that shows each parameter, the welding conditions may be set to a combination of parameters that are inscribed in the region judged as good and located within the sphere having the maximum volume, similar to the case when there are two parameters as described above. Similarly, the welding conditions may be set to a combination of distance parameters that are within a predetermined percentage range of the radius of the sphere from the centroid (center) of such a sphere having the maximum volume. In this case, it is preferable to set the welding conditions to a combination of parameters that are within 80% of the radius from the centroid (center) of the sphere as the predetermined percentage. In this context, "center of gravity" refers to the center of mass in the shape being calculated, assuming a uniform mass distribution. Furthermore, the distance from the center of gravity (center) relative to the radius (circle: 70%, sphere: 80%) is the distance at which a combination of parameters is selected, for example, where the area and volume are located within approximately 50% of the center of gravity (center).

[0104] Figures 17 and 18 illustrate other examples of welding condition settings. For example, if there are two parameters (parameters A and B) and the good judgment result is represented in a two-dimensional space representing each parameter, the analysis unit 13 determines, as shown in Figure 17, that among the plots judged as good for parameter A, the line segment L with the longest axial distance representing parameter A is the line segment L. A Midpoint PAM And, among the plots judged as good for parameter B, the line segment L has the longest distance in the axis direction that represents parameter B. B Midpoint P BM Line segment L connecting to M Midpoint P M1 Set the corresponding parameters A and B in the welding conditions.

[0105] Furthermore, if there are three parameters (parameters A to C) and the good judgment result is represented in a three-dimensional space representing each parameter, the analysis unit 13, as shown in Figure 18, determines the region R formed by the group of plots judged as good for parameters A and B. AB The center of gravity P ABM And the region R formed by the group of plots judged as good for parameters B and C. BC The center of gravity P BCM The region R is formed by the group of plots that are judged as good for parameters A and C. AC The center of gravity P ACM The triangle T is formed by and M The center of gravity P M2 Set the corresponding parameters A to C in the welding conditions. In addition, as shown in Figure 17, the longest line segment in each two-dimensional plane can be determined, the centroid of the triangle formed by connecting the midpoints of these line segments can be calculated, and parameters A to C corresponding to this centroid can be set as welding conditions. In this case, weighting may be applied according to the parameter type.

[0106] Thus, in Modification 2, the good welding condition is plotted based on the weld shape estimated from the arc welding conditions, and the optimal welding conditions are set according to the pattern of the cells judged as good in the map. According to this embodiment, as with the embodiment, the welding conditions are set to conditions that ensure good welding even with slight deviations in the conditions within the judgment space, among the conditions that result in good welding, so that welding conditions with a margin of error can be set in automatic welding.

[0107] In the embodiments and variations described above, the parameters set for each layer may differ depending on the evaluation items for each layer, or the parameters may need to be reviewed depending on the degree of influence. Figure 19 is a diagram illustrating the relationship between welding quality evaluation items and welding condition parameters. In Figure 19, the initial layer, laminated layer, and surface layer represent layers formed by the weld, and the weld is formed in this order. Also, in Figure 19, darker hatching indicates a greater influence. For example, in the initial layer, the influence of welding condition parameters such as current, voltage, and oscillation width (welding operation width) is relatively large on the root penetration at the butt joint surface of the members and the toe shape of the weld. In this case, if the root penetration is judged as good but the toe shape is judged as poor in the above combination of welding condition parameters in the initial layer, it is necessary to review the welding condition parameters. At this time, the welding condition setting device 10 notifies the user via the input / output unit 12 to review the welding condition parameters.

[0108] (Recording medium) In the embodiment described above, a program that causes the learning device 2 and the state determination device 3 to execute a processing method can be recorded on a recording medium that can be read by a computer or other machine or device such as a wearable device (hereinafter referred to as "computer, etc."). By having the computer, etc. read and execute the program on this recording medium, the computer, etc. functions as a mobile device control device. Here, a recording medium that can be read by a computer, etc. refers to a non-temporary recording medium that stores information such as data and programs by electrical, magnetic, optical, mechanical, or chemical action and can be read by a computer, etc. Examples of such recording media that can be removed from a computer, etc. include flexible disks, magneto-optical disks, CD-ROMs, CD-R / Ws, DVDs, BDs, DATs, magnetic tapes, and memory cards such as flash memory. In addition, recording media that are fixed to a computer, etc. include hard disks and ROMs. Furthermore, SSDs can be used as both a recording medium that can be removed from a computer, etc. and a recording medium that is fixed to a computer, etc.

[0109] Although one embodiment of the present invention has been described in detail above, the present invention is not limited to the above-described embodiment, and various modifications are possible based on the technical idea of ​​the present invention. For example, the prediction model given in the above-described embodiment is merely an example, and different models, such as models for calculating the heat conduction distribution, penetration shape, and surface shape of the weld, may be used as needed, and the present invention is not limited by the description and drawings that constitute part of the disclosure of the present invention in this embodiment.

[0110] Furthermore, in one embodiment, the terms "part" as described above can be replaced with "circuit" or the like. For example, the control unit can be replaced with a control circuit.

[0111] Further effects and modifications can be readily derived by those skilled in the art. Broader aspects of this disclosure are not limited to the specific details and representative embodiments expressed and described above. Accordingly, various modifications are possible without departing from the spirit or scope of the overall concept of the invention as defined by the appended claims and their equivalents. [Explanation of Symbols]

[0112] 10. Welding condition setting device 11 Communications Department 12 Input / output section 13 Analysis Department 14 Condition Setting Section 15 Control Unit 16 Memory section

Claims

1. A welding condition setting method for setting welding conditions for joining members together, A precondition setting step that sets preconditions including fixed values ​​related to the members to be joined and multiple sets of welding condition parameters, each consisting of multiple different parameter types, A weld shape prediction step in which the shape of the weld formed by welding under the above preconditions is predicted for each set of welding condition parameters, A determination step to determine the quality of each predicted weld shape, A determination step in which a set of welding condition parameters to be set as welding conditions is determined from among the sets of welding condition parameters that were judged to be good in the judgment step, A welding condition setting method including the following.

2. The welding condition setting method according to claim 1, wherein the determination step includes a first parameter set selection step of extracting as a candidate welding condition parameter set that satisfies a first condition from among the welding condition parameter sets that were judged to be good in the judgment step, and a second parameter set selection step of setting as a welding condition a set of welding condition parameters that satisfies a second condition different from the first condition from among the welding condition parameter sets selected in the first parameter set selection step.

3. The first parameter set selection step involves extracting candidate welding condition parameter sets for each of the welding condition parameter sets that were judged as good in the judgment step by assigning points based on predetermined weights as the first condition, The welding condition setting method according to claim 2, wherein the second parameter set selection step is to set a welding condition with a predetermined score or higher from among the candidate welding condition parameter sets that have been scored, as the second condition.

4. The determination step includes a region setting step in which a region is set by extracting a welding condition parameter set that satisfies the first condition as a candidate from among the welding condition parameter sets that were judged to be good in the judgment step, A welding condition setting method according to claim 1, further comprising a condition determination step of determining a set of welding condition parameters within the region set in the region setting step as a welding condition.

5. The welding condition setting method according to claim 4, wherein the set of welding condition parameters to be determined in the determination step is a set of welding condition parameters located at the midpoint or centroid of the shape formed by the contour of the region set in the region setting step.

6. The aforementioned parameter types are two: The aforementioned decision step is, In the judgment map showing the judgment results of the parameter set, the parameter set where the centroid of the region judged as good is located is set as the welding condition. The welding condition setting method according to claim 5.

7. The aforementioned parameter types are two: In the Cartesian coordinate system in which the region is formed in the region setting step, a set of parameters located within the circle that is inscribed in the region formed by the good judgment and has the largest area is set as the welding condition. The welding condition setting method according to claim 4.

8. The welding condition setting method according to claim 7, wherein the set of parameters set as welding conditions is a set of parameters located within a radius of 70% from the centroid of the circle having the largest area.

9. The welding condition setting method according to claim 8, wherein the set of parameters set as welding conditions is the set of parameters in which the centroid of the circle having the largest area is located.

10. The aforementioned parameter types are three: In the region setting step, the welding conditions are set to a set of parameters that are located inside a sphere that is inscribed in the region formed by the good judgment and has the largest volume in the orthogonal coordinate system in which the region is formed. The welding condition setting method according to claim 4.

11. The welding condition setting method according to claim 10, wherein the set of parameters set as welding conditions is a set of parameters located within 80% of the radius from the center of gravity of the sphere having the maximum volume.

12. The welding condition setting method according to claim 11, wherein the set of parameters set as welding conditions is a set of parameters located at the centroid of the sphere having the maximum volume.

13. The aforementioned parameter types are two: In the two-dimensional Cartesian coordinate system in which the region is formed in the region setting step, the welding conditions are set to a set of parameters where the midpoint of the line segment connecting the first midpoint of the range of one parameter that provides the widest range of good judgments for the other parameter and the second midpoint of the range of the other parameter that provides the widest range of good judgments for the one parameter is located. The welding condition setting method according to claim 5.

14. The aforementioned parameter types are three: In the aforementioned region setting step, the set of parameters where the centroid of the triangle formed by connecting the centroids of the good judgment regions in each of the three two-dimensional orthogonal coordinate systems in which the region is formed is located is set as the welding condition. The welding condition setting method according to claim 5.

15. The members are joined together by the formation of multiple welds. The weld shape prediction step predicts the weld shape for each set of welding condition parameters for the formation of each weld, The determination step determines, for each weld, the quality of the weld shape for each set of predicted welding condition parameters. The aforementioned decision step involves setting the welding conditions for each weld. The welding condition setting method according to claim 1.

16. A welding condition setting program that causes a computer to set welding conditions for joining components together, A precondition setting step that sets preconditions including fixed values ​​related to the members to be joined and multiple sets of welding condition parameters, each consisting of multiple different parameter types, A weld shape prediction step in which the shape of the weld formed by welding under the above preconditions is predicted for each set of welding condition parameters, A determination step to determine the quality of the weld for each predicted set of weld shapes, A determination step in which a set of welding condition parameters to be set as welding conditions is determined based on the good judgment of the weld shape determined in the above determination step, A welding condition setting program that causes the computer to execute the above.

17. The aforementioned decision step is, A first parameter set selection step involves extracting and calculating a candidate welding condition parameter set that satisfies the first condition from among the welding condition parameter sets that were judged to be good in the judgment step, A second parameter set selection step is performed to set a set of welding condition parameters that satisfy a second condition different from the first condition, from among the welding condition parameter sets selected in the first parameter set selection step, as the welding condition, A welding condition setting program according to claim 16, including the following:

18. A welding condition setting device for setting welding conditions for joining members together, A precondition setting unit sets preconditions including fixed values ​​related to the members to be joined and multiple sets of welding condition parameters, each consisting of a set of different parameter types. An analysis unit predicts the shape of the weld formed by welding under the aforementioned preconditions for each set of welding condition parameters, and determines the quality of the weld for each predicted set of weld shapes. A condition setting unit determines a set of welding condition parameters to be set as welding conditions based on the good judgment of the weld shape determined by the analysis unit, A welding condition setting device equipped with the following features.

19. The welding condition setting device according to claim 18, wherein the condition setting unit performs a first parameter set selection by extracting as a candidate welding condition parameter set that satisfies a first condition from among the welding condition parameter sets that have been judged as good by the analysis unit, and sets as a welding condition a set of welding condition parameters that satisfies a second condition different from the first condition from among the selected welding condition parameter sets.

Images