Welding waveform control device and welding waveform control method

Abstract

To provide a welding waveform control device and welding waveform control method that can generate a welding waveform to obtain the desired welding result in a short time and easily while evaluating welding.SOLUTION: A welding waveform control device 100 includes: a welding waveform acquisition unit 110 that acquires the welding waveform during the welding; a welding evaluation unit 130 that evaluates the welding on the basis of the acquired welding waveform; an output unit 140 that outputs the evaluation result; an adjustment information acquisition unit 150 that acquires adjustment information of the desired welding for the evaluation result; and a welding waveform generation unit 160 that generates the welding waveform on the basis of the acquired welding waveform and the adjustment information of the desired welding.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a welding waveform control device and a welding waveform control method. [Background technology]

[0002] 2. Description of the Related Art In recent years, many robots have come into widespread use in the industrial world. The robots are used, for example, in the assembly, welding, and transportation of electronic and mechanical parts, and are contributing to the efficiency and automation of factory production lines.

[0003] With welding robots, there is a demand to shorten welding times and takt times to improve the efficiency of production lines, but at the same time, welding quality must be ensured, taking into account the bead finish in arc welding.

[0004] In general, the desired welding results (bead finish, etc.) are obtained by adjusting welding conditions such as welding speed, welding time, welding current, and welding voltage.

[0005] For example, Patent Document 1 discloses a technique for shortening the cycle time and stabilizing the welding result in a good condition by appropriately adjusting the welding conditions using a neural network. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Patent Publication No. 2021-159969 Summary of the Invention [Problem to be solved by the invention]

[0007] However, while the technology disclosed in Patent Document 1 can shorten the cycle time and stabilize the welding results in a good condition, users have various detailed requests regarding the finish of the welding, and further improvements are required.

[0008] Meanwhile, a method is also known in which a welding waveform, such as a welding current waveform and / or a welding voltage waveform, is adjusted during welding to meet the specific needs of a user regarding a desired welding result. Adjustment of such a welding waveform is highly dependent on the skill of the worker, and even if the worker is an expert, it may take a huge amount of time to obtain the desired welding result, which is not easy.

[0009] Therefore, an object of the present invention is to provide a welding waveform control device and a welding waveform control method that can easily generate a welding waveform for obtaining a desired welding result in a short time while evaluating the welding. [Means for solving the problem]

[0010] A welding waveform control device according to one embodiment of the present invention includes a welding waveform acquisition unit that acquires a welding waveform during welding, a welding evaluation unit that evaluates the welding based on the acquired welding waveform, an output unit that outputs the evaluation result, an adjustment information acquisition unit that acquires desired welding adjustment information for the evaluation result, and a welding waveform generation unit that generates a welding waveform based on the acquired welding waveform and the desired welding adjustment information.

[0011] According to this aspect, the welding evaluation unit evaluates the welding based on the welding waveform at the time of welding acquired by the welding waveform acquisition unit. The output unit outputs the result evaluated by the welding evaluation unit, and the adjustment information acquisition unit acquires desired welding adjustment information for that result. Then, the welding waveform generation unit generates a welding waveform based on the welding waveform acquired by the welding waveform acquisition unit and the desired welding adjustment information. This makes it possible to easily generate a welding waveform for obtaining a desired welding result in a short time while evaluating the welding. As a result, the user can perform the welding desired by rewelding using the generated welding waveform.

[0012] In the above aspect, the welding apparatus may further include a feature extraction unit that extracts features based on the acquired welding waveform, the welding evaluation unit evaluates the welding based on the extracted features, and the welding waveform generation unit generates a welding waveform based on the extracted features and desired welding adjustment information.

[0013] According to this aspect, the feature extraction unit extracts feature values ​​based on the welding waveform acquired by the welding waveform acquisition unit, the welding evaluation unit evaluates the welding based on the feature values, and the welding waveform generation unit generates the welding waveform based on the feature values ​​and the desired welding adjustment information. This allows the welding evaluation and welding waveform generation to be appropriately evaluated and the welding waveform desired by the user to be generated while reducing the processing load. Furthermore, the outputted welding evaluation results and factors and influences on the generated welding waveform can be confirmed and analyzed.

[0014] In the above aspect, the welding evaluation unit may evaluate the welding based on the extracted feature amount using a first machine learning model that uses the feature amount as input data and an evaluation of the welding as output data.

[0015] According to this aspect, the welding evaluation unit evaluates the welding using the machine learning model based on the feature amount, and the output unit outputs the evaluation result. Since the feature amount is extracted from the welding waveform and the welding is evaluated using the machine learning model based on the feature amount, the welding can be appropriately evaluated while reducing the processing load.

[0016] In the above aspect, the welding waveform generation unit may generate a welding waveform based on the extracted features and desired welding adjustment information using a second machine learning model that uses features based on the welding waveform and welding adjustment information as input data and waveform control parameters for generating the welding waveform as output data.

[0017] According to this aspect, the welding waveform generator uses the feature amount and welding adjustment information as input data and generates a welding waveform using a machine learning model and waveform control parameters as output data. As a result, the adjustment of the welding waveform is less dependent on the skill of the worker, and the repetition of welding and adjustment is reduced, making it possible to easily generate a welding waveform for obtaining a desired welding result in a short time.

[0018] A welding waveform control method according to one aspect of the present invention is a welding waveform control method executed by a welding waveform control device that controls a welding waveform during welding, and includes a welding waveform acquisition step of acquiring a welding waveform during welding, a welding evaluation step of evaluating the welding based on the acquired welding waveform, an output step of outputting the evaluation result, an adjustment information acquisition step of acquiring desired welding adjustment information for the evaluation result, and a welding waveform generation step of generating a welding waveform based on the acquired welding waveform and the desired welding adjustment information.

[0019] According to this aspect, in the welding evaluation step, the welding is evaluated based on the welding waveform during welding acquired in the welding waveform acquisition step. In the output step, the result of the evaluation in the welding evaluation step is output, and in the adjustment information acquisition step, desired welding adjustment information for that result is acquired. Then, in the welding waveform generation step, a welding waveform is generated based on the welding waveform acquired in the welding waveform acquisition step and the desired welding adjustment information. This makes it possible to easily generate a welding waveform for obtaining a desired welding result in a short time while evaluating the welding. As a result, by rewelding using the generated welding waveform, the user can perform the welding desired. Effect of the Invention

[0020] An object of the present invention is to provide a welding waveform control device and a welding waveform control method that can easily generate a welding waveform for obtaining a desired welding result in a short time while evaluating the welding. [Brief description of the drawings]

[0021] [Figure 1] FIG. 1 is a system schematic diagram showing a welding robot system 10 according to an embodiment of the present invention. [Diagram 2] 1 is a functional block diagram showing each function of a welding waveform control device 100 according to an embodiment of the present invention. [Diagram 3] 4 is a diagram showing feature quantities extracted from a welding current waveform acquired by a welding waveform acquisition unit 110. FIG. [Figure 4] FIG. 13 is a diagram showing how an evaluation result is output using a machine learning model (first machine learning model) with feature amounts extracted from a welding current waveform as input data. [Diagram 5] FIG. 13 is a diagram showing how a welding current waveform is used as input data, and a single machine learning model is used to produce multiple evaluation items related to welding as output data. [Figure 6] FIG. 13 is a diagram showing how waveform control parameters are output using a machine learning model (second machine learning model) with feature amounts extracted from a welding current waveform and desired welding adjustment information as input data. [Figure 7] FIG. 13 is a diagram showing how a welding current waveform and welding adjustment information are used as input data, and a waveform control parameter is output using one machine learning model. [Figure 8] 13 is a diagram showing an adjusted welding current waveform generated by a welding waveform generating unit 160. FIG. [Figure 9] 4 is a flowchart showing a welding waveform control method M100 executed by a welding waveform control device 100 according to one embodiment of the present invention. [Figure 10] 4 is a diagram showing feature quantities extracted from a welding voltage waveform acquired by a welding waveform acquisition unit 110. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0022] Hereinafter, an embodiment of the present invention will be specifically described with reference to the drawings. Note that the embodiment described below is merely a specific example for carrying out the present invention, and is not intended to limit the interpretation of the present invention. In addition, in order to facilitate understanding of the description, the same reference numerals are used as far as possible for the same components in each drawing, and duplicated descriptions may be omitted.

[0023] <One embodiment> [Welding robot system overview] 1 is a system schematic diagram showing a welding robot system 10 according to an embodiment of the present invention. In FIG. 1, the welding robot system 10 includes a welding robot 20, a teach pendant 30, a robot controller 40, and a power source 50.

[0024] Welding robot 20 is connected to robot controller 40 via a cable, and performs arc welding based on operation commands from robot controller 40. Welding robot 20 is equipped with welding torch 21 at the tip of its arm, and performs arc welding by feeding welding wire from the tip of welding torch 21 and generating an arc between the welding wire and the base material (workpiece made of a metallic material) that is to be welded.

[0025] Welding torch 21 is connected to power source 50 via a cable, and receives a welding voltage and a welding current to the welding wire. In arc welding, when the welding wire is momentarily brought into contact with a metal material and electricity is passed through it, an arc discharge occurs between the welding wire and the metal material, and the heat of the generated arc melts the welding wire and the metal material, thereby performing welding.

[0026] The teach pendant 30 receives input from a worker performing welding work regarding welding-related teaching information for the welding robot 20. The worker inputs optimal welding-related teaching information using the teach pendant 30 while checking the state of the arc.

[0027] Here, the welding-related teaching information is information related to the welding performed by the welding robot 20, and includes teaching information for teaching the operation of the welding robot 20 and welding execution conditions.

[0028] The teaching information for welding robot 20 includes information regarding the operation of the arm of welding robot 20, information regarding the position and posture of welding robot 20, information regarding the protruding length of the welding wire fed from the tip of welding torch 21, and the like.

[0029] The welding conditions also include the welding voltage applied to the welding wire, the value of the welding current flowing through the welding wire, the welding speed and stop time representing the moving speed of the welding torch 21 in the welding line direction during welding, and may further include the wire feeding speed controlled by the wire feeding device.

[0030] The robot controller 40 is a device that controls the welding robot 20. The robot controller 40 is connected to the teach pendant 30 and can acquire welding-related teaching information input to the teach pendant 30. The robot controller 40 controls the welding robot 20 and the power source 50 based on the welding-related teaching information.

[0031] Power supply 50 is connected to welding robot 20 via a cable, and supplies a welding voltage and a welding current to welding torch 21 in welding robot 20 based on commands from robot control device 40 .

[0032] 1, the teach pendant 30 is connected to the robot control device 40 via a cable, but may be connected wirelessly. That is, the teach pendant 30 and the robot control device 40 may be provided with a communication unit that performs wireless communication. By connecting the robot control device 40 and the teach pendant 30 wirelessly, the worker can input welding-related teaching information while moving freely without being bothered by the presence of a cable or being restricted in the range of movement by the length of the cable.

[0033] In this manner, in the welding robot system 10, the robot control device 40 operates the welding robot 20 to perform arc welding.

[0034] [Welding waveform control device configuration] Hereinafter, a welding waveform control device that controls the welding waveform during welding performed as described above will be described.

[0035] 2 is a functional block diagram showing each function of the welding waveform control device 100 according to one embodiment of the present invention. As shown in FIG. 2, the welding waveform control device 100 includes a welding waveform acquisition unit 110, a feature extraction unit 120, a welding evaluation unit 130, an output unit 140, an adjustment information acquisition unit 150, a welding waveform generation unit 160, and a storage unit 170. All or a part of the units having these functions in the welding waveform control device 100 may be included in the above-mentioned welding robot 20, the teach pendant 30, the robot control device 40, other peripheral devices, and a computer such as a personal computer or a display device such as a monitor, and the welding waveform control device 100 may be configured by each unit having these functions.

[0036] The welding waveform acquisition unit 110 acquires a welding waveform during welding. For example, the welding waveform acquisition unit 110 acquires a welding current waveform and / or a welding voltage waveform during a period during which welding is performed by the welding robot 20. The period during which welding is performed may be every predetermined time, or may be every welding work in a predetermined section.

[0037] The feature amount extraction unit 120 extracts feature amounts based on the welding waveform acquired by the welding waveform acquisition unit 110. For example, the feature amount extraction unit 120 may extract a preset element as a feature amount from the welding current waveform and / or the welding voltage waveform.

[0038] Fig. 3 is a diagram showing feature quantities extracted from the welding current waveform acquired by welding waveform acquisition unit 110. As shown in Fig. 3, each of the following elements is extracted as feature quantities from the welding current waveform: (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time.

[0039] When extracting each of these elements as feature quantities from the welding current waveform, the feature quantities may be extracted, for example, from the welding current waveform at a predetermined time during the stable period excluding the start and end of welding. At the start and end of welding, different control is performed from that during the stable period, and therefore the welding current waveform is different, so there is a possibility that appropriate feature quantities cannot be extracted.

[0040] Furthermore, each element extracted as a feature may be calculated using its average value, standard deviation, or variance. For example, with the pulse interval (c) shown in Fig. 3 being one cycle, each of the elements (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time may be extracted from a welding current waveform for multiple cycles, and the average value of each may be calculated to determine the feature value of each element. This reduces the variation in each element, and allows each element to be more appropriately extracted as a feature.

[0041] In addition, the elements are defined as (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time here, but are not limited to these. For example, only one or more of these elements may be extracted as a feature, or other elements (e.g., rise slope, fall slope, short circuit current, short circuit release current, short circuit time, number of short circuits, etc.) may be extracted as features as long as they can be extracted from the welding current waveform and can affect the evaluation of welding. The elements to be extracted may be selectable and set by the user in advance.

[0042] Furthermore, the feature extraction unit 120 may extract the feature using a machine learning model. For example, the welding current waveform may be used as input data, and a machine learning model may be used to output each of the above-mentioned elements such as (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time as a feature. Here, the machine learning model may also be used to determine which element to output. By using the fed-back trained model, each element can be extracted as a more appropriate feature.

[0043] The welding evaluation unit 130 evaluates welding using a machine learning model (first machine learning model) based on the feature amounts extracted by the feature amount extraction unit 120. For example, the welding evaluation unit 130 evaluates welding using the machine learning model with the elements of (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time as input data, which are the feature amounts described in Fig. 3 .

[0044] FIG. 4 is a diagram showing a state in which the feature amount extracted from the welding current waveform is used as input data and an evaluation result is output using a machine learning model (first machine learning model). As shown in FIG. 4, the input data are each of the elements of (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time, and the machine learning model is used to output a welding evaluation result for a plurality of evaluation items related to welding, such as (A) bead width, (B) bead height, (C) undercut, and (D) spatter amount. For each evaluation item, for example, a score on a five-level scale of "1" to "5" ("1" being the worst, "3" being the standard, and "5" being the best) may be output as the evaluation result, or further, a single score may be output by combining them as the evaluation result.

[0045] The machine learning model used here is not particularly limited, but for example, LightGBM, random forest, and support vector machine reduce the processing load compared to algorithms using neural networks.

[0046] In addition, when outputting multiple evaluation results as shown in Figure 4, a machine learning model capable of outputting multiple evaluation results may be used, or multiple machine learning models each outputting one evaluation result may be used.

[0047] The evaluation items are (A) bead width, (B) bead height, (C) undercut, and (D) spatter amount, but are not limited to these. For example, only one or more of these elements may be the evaluation items, or other evaluation items (e.g., penetration, blowholes, etc.) may be output as evaluation items as long as they are elements that can evaluate welding. The user may be able to select and set in advance which evaluation items are to be output, and in that case, a machine learning model corresponding to the evaluation items may be provided.

[0048] Furthermore, the welding waveform control device 100 may include a welding condition acquisition unit. The welding condition acquisition unit acquires the welding execution conditions (welding execution conditions set by the operator) when the welding robot 20 performs welding. The welding execution conditions include, for example, a welding current value, a welding voltage value, a welding speed, a stop time, an arc generation time, an arc stop time, a pitch interval, and a cooling time, and may further include a wire feed speed controlled by a wire feeder. The values ​​of the welding execution conditions acquired here may be actual measured values, or, when it is difficult to acquire measured values, they may be set values ​​set by the operator or output command values ​​from the welding robot 20.

[0049] The welding evaluation unit 130 may evaluate the welding using a machine learning model based on the welding conditions acquired by the welding condition acquisition unit in addition to the feature values ​​extracted by the feature extraction unit 120. Specifically, in the machine learning model shown in FIG. 4, in addition to the feature values ​​extracted from the welding current waveform, the welding conditions acquired by the welding condition acquisition unit (for example, welding execution conditions such as welding current value, welding voltage value, welding speed, stop time, arc generation time, arc stop time, pitch interval, and cooling time) may be used as input data, and multiple evaluation items related to welding such as (A) bead width, (B) bead height, (C) undercut, and (D) spatter amount may be output as evaluation results of welding. For this, it is sufficient to have a machine learning model that uses the feature values ​​extracted by the feature extraction unit 120 and the welding conditions acquired by the welding condition acquisition unit as input data and outputs multiple evaluation items related to welding such as (A) bead width, (B) bead height, (C) undercut, and (D) spatter amount as output data. As a result, the welding can be evaluated more appropriately.

[0050] Here, feature extraction unit 120 extracts feature amounts from the welding current waveform, and welding evaluation unit 130 evaluates welding using a machine learning model with the extracted feature amounts as input data and multiple evaluation items related to welding as output data. In addition, when feature amount extraction unit 120 extracts feature amounts, this includes extracting feature amounts using a machine learning model with the welding current waveform as input data, but for example, welding may be evaluated using one machine learning model with the welding current waveform as input data and multiple evaluation items related to welding as output data.

[0051] Fig. 5 is a diagram showing how a welding current waveform is used as input data and a single machine learning model is used to output multiple evaluation items related to welding as output data. As shown in Fig. 5, the welding current waveform is used as input data and a machine learning model is used to output multiple evaluation items related to welding, such as (A) bead width, (B) bead height, (C) undercut, and (D) spatter amount, as welding evaluation results.

[0052] Here, one machine learning model is, for example, a recurrent neural network (RNN) such as a long short-term memory (LSTM), and includes a feature extraction layer. The feature extraction layer may be configured to extract the following elements as intermediate data: (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time.

[0053] For example, the machine learning model may be configured using a fully connected layer in a feature extraction layer that uses the welding current waveform as input data and extracts feature values ​​(each element of (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time) as extracted data, and outputs multiple evaluation items related to welding, such as (A) bead width, (B) bead height, (C) undercut, and (D) spatter amount.

[0054] Here, the single machine learning model is an RNN, but is not limited to this. For example, LightGBM, random forest, and support vector machine may be used as a single machine learning model as long as welding can be evaluated using the welding current waveform as input data and multiple evaluation items related to welding as output data.

[0055] Returning to the description of Fig. 2, the output unit 140 outputs the results of the evaluation performed by the welding evaluation unit 130. For example, the results may be output to a monitor or to a display screen of a tablet or dedicated terminal.

[0056] The adjustment information acquisition unit 150 acquires adjustment information for a desired welding. For example, the adjustment information acquisition unit 150 receives adjustment information for welding desired by a user who has confirmed the welding result performed by the welding robot 20 (the welding evaluation result output by the output unit 140), and acquires the adjustment information for the welding.

[0057] Specifically, when the user checks the welding result performed by the welding robot 20 (the evaluation result of the welding output by the output unit 140), if the user wants to make the bead width a little thicker, the adjustment item "bead width" and the adjustment amount "+1" are input as the adjustment information of the desired welding, and the adjustment information acquisition unit 150 acquires the adjustment information of the welding. As an input mode of the adjustment amount, when the user wants to make the bead width a little thicker, the adjustment amount "+1" is given as an example, but when the user wants to make it thicker, "+2" or "+3" may be used, and when the user wants to make it thinner, "-1", "-2", "-3", etc. may be used depending on the degree of the adjustment. The adjustment amount per step may be preset depending on the welding target. Also, the user may input "+10%", "-10%", "+1 cm", "-1 cm", etc., and the adjustment information acquisition unit 150 may acquire a more specific adjustment amount.

[0058] The adjustment item is not limited to the bead width, and may be, for example, a bead height, a spatter amount, an undercut, penetration, a blow hole, etc. For example, when the user wants to reduce the amount of spatter, the user inputs the adjustment item as "spatter amount" and the adjustment amount as "-1", "-2", "-3", "-10%, "-20%, "-30%, etc." according to the degree of the amount of spatter, and the adjustment information acquisition unit 150 acquires the adjustment information of the welding (adjustment item "spatter amount", adjustment amount "-1", etc.). As a specific example, when the welding evaluation unit 130 evaluates the amount of spatter as "2" out of five levels ("1" very much, "2" much, "3" normal, "4" little, "5" very little), if the user wants to reduce the amount of spatter, the user may input the adjustment item "spatter amount" and the adjustment amount "-1 (meaning to reduce)" as the adjustment information of the welding, or may input the adjustment item "spatter amount" and the evaluation "3 (meaning that it is normal in the five-level evaluation). That is, the user may input a difference from the evaluation of welding by welding evaluation unit 130, or may input a desired target value (evaluation value).

[0059] Furthermore, the user can select multiple adjustment items, for example, if the user wants to make the bead width a little wider and reduce the amount of spatter, the user may input the adjustment item "bead width" and the adjustment amount "+1", and further input the adjustment item "amount of spatter" and the adjustment amount "-1". Then, the adjustment information acquisition unit 150 acquires the multiple adjustment items and the corresponding adjustment amounts as welding adjustment information.

[0060] The welding waveform generation unit 160 generates a welding waveform using a machine learning model (second machine learning model) based on the features extracted by the feature extraction unit 120 and the welding adjustment information acquired by the adjustment information acquisition unit 150.

[0061] Here, the machine learning model takes as input data feature quantities based on a welding waveform and welding adjustment information, and outputs waveform control parameters for generating a welding waveform, and is stored in advance in storage unit 170. For example, the machine learning model takes as input data the elements of (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time as feature quantities described in Fig. 3, as well as welding adjustment information including adjustment items and adjustment amounts for the adjustment items, and outputs waveform control parameters for generating a welding current waveform.

[0062] The adjustment items as input data are, for example, bead width, bead height, spatter amount, undercut, penetration, blowhole, etc., and the adjustment amount is indicated by "-3" to "+3" etc. corresponding to each adjustment item. The waveform control parameters as output data are parameters for generating a welding waveform, and are each element of "adjusted pulse current", "adjusted base current", "adjusted pulse interval", "adjusted pulse time", "adjusted rise time", and "adjusted fall time" adjusted from the welding current waveform shown in Fig. 3 as input data. More specifically, the waveform control parameters are parameters for configuring the shape of the welding waveform.

[0063] Fig. 6 is a diagram showing how the feature quantity extracted from the welding current waveform and the desired welding adjustment information are used as input data, and the waveform control parameters are output using a machine learning model (second machine learning model). As shown in Fig. 6, the input data are the elements of (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time, and the welding adjustment information desired by the user (adjustment item "bead width" and the adjustment amount "+1" for the adjustment item), and the machine learning model is used to output the elements of (A) adjusted pulse current, (B) adjusted base current, (C) adjusted pulse interval, (D) adjusted pulse time, (E) adjusted rise time, and (F) adjusted fall time as waveform control parameters.

[0064] Here, a user who has checked the welding result (the welding evaluation result output by the output unit 140) performed by the welding robot 20 wants to make the bead width a little thicker, and the adjustment information acquisition unit 150 acquires the adjustment information of the welding. Then, the welding waveform generation unit 160 uses a machine learning model based on the feature amount (each element of (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time) extracted by the feature amount extraction unit 120 and the welding adjustment information (adjustment item "bead width" and adjustment amount "+1") acquired by the adjustment information acquisition unit 150 to generate a welding current waveform using each element of the adjusted (A) adjusted pulse current, (B) adjusted base current, (C) adjusted pulse interval, (D) adjusted pulse time, (E) adjusted rise time, and (F) adjusted fall time as waveform control parameters. In other words, the welding current waveform generated by welding waveform generation unit 160 is a welding current waveform that has been adjusted from the welding current waveform acquired by welding waveform acquisition unit 110 so that the bead width is slightly wider.

[0065] The machine learning model used here is not particularly limited, but for example, LightGBM, random forest, and support vector machine reduce the processing load compared to algorithms using neural networks.

[0066] Furthermore, when multiple elements are output as waveform control parameters as shown in FIG. 6, a machine learning model capable of outputting multiple elements may be used, or multiple machine learning models each outputting one element may be used.

[0067] Furthermore, when the welding waveform control device 100 includes the above-mentioned welding condition acquisition unit, the welding current waveform may be generated using a machine learning model with each element adjusted from the welding current waveform during welding as a waveform control parameter based on the welding conditions acquired by the welding condition acquisition unit, in addition to the feature extracted by the feature extraction unit 120 and the welding adjustment information acquired by the adjustment information acquisition unit 150. Specifically, in the machine learning model shown in FIG. 6, in addition to the feature extracted from the welding current waveform during welding and the welding adjustment information, the welding conditions acquired by the welding condition acquisition unit (for example, welding execution conditions such as welding current value, welding voltage value, welding speed, stop time, arc generation time, arc stop time, pitch interval, and cooling time) are used as input data, and a welding current waveform is generated with each element of the adjusted (A) adjusted pulse current, (B) adjusted base current, (C) adjusted pulse interval, (D) adjusted pulse time, (E) adjusted rise time, and (F) adjusted fall time as a waveform control parameter. This can be achieved by providing a machine learning model that uses the features extracted by feature extraction unit 120, the welding adjustment information acquired by adjustment information acquisition unit 150, and the welding conditions acquired by the welding condition acquisition unit as input data, and outputs each of the adjusted elements of (A) adjusted pulse current, (B) adjusted base current, (C) adjusted pulse interval, (D) adjusted pulse time, (E) adjusted rise time, and (F) adjusted fall time as waveform control parameters.

[0068] In this example, feature extraction unit 120 extracts features from the welding current waveform, adjustment information acquisition unit 150 acquires welding adjustment information desired by the user, and welding waveform generation unit 160 generates a welding current waveform using the extracted features and the acquired welding adjustment information as input data and a machine learning model to generate waveform control parameters as output data. In addition, when feature extraction unit 120 extracts features, this includes extracting features using a machine learning model with the welding current waveform as input data, but for example, a welding current waveform may be generated using one machine learning model with the welding current waveform and welding adjustment information as input data and waveform control parameters as output data.

[0069] Fig. 7 is a diagram showing how the welding current waveform and welding adjustment information are used as input data, and a single machine learning model is used to output waveform control parameters. As shown in Fig. 7, the welding current waveform and welding adjustment information are used as input data, and a machine learning model is used to output each element, such as (A) adjusted pulse current, (B) adjusted base current, (C) adjusted pulse interval, (D) adjusted pulse time, (E) adjusted rise time, and (F) adjusted fall time, as waveform control parameters.

[0070] Here, one machine learning model is, for example, a recurrent neural network (RNN) such as a long short-term memory (LSTM), and includes a feature extraction layer. The feature extraction layer may be configured to extract the following elements as intermediate data: (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time.

[0071] For example, the machine learning model may be configured using a fully connected layer in a feature extraction layer in which the welding current waveform and welding adjustment information are used as input data and the features of the welding current waveform (each of the elements of (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time) are used as extracted data, and the machine learning model may output data in the form of each element (waveform control parameter) such as (A) adjusted pulse current, (B) adjusted base current, (C) adjusted pulse interval, (D) adjusted pulse time, (E) adjusted rise time, and (F) adjusted fall time.

[0072] Here, the single machine learning model is an RNN, but this is not limited to this. For example, LightGBM, random forest, and support vector machine may also be used as a single machine learning model as long as the welding current waveform can be generated using the welding current waveform and welding adjustment information as input data and the waveform control parameters as output data.

[0073] In this manner, the welding waveform generated by the welding waveform generating unit 160 may be output, for example, to a monitor or to a display screen of a tablet or dedicated terminal.

[0074] Fig. 8 is a diagram showing the adjusted welding current waveform generated by welding waveform generation unit 160. As shown in Fig. 8, a welding current waveform adjusted so that the bead width is slightly wider is generated from the welding current waveform acquired by welding waveform acquisition unit 110. This indicates that a user checks the welding result performed by welding robot 20 (the welding evaluation result output by output unit 140) and inputs desired welding adjustment information (adjustment item "bead width" and adjustment amount "+1"), and an adjusted welding current waveform that is appropriately adjusted to meet the user's request is generated.

[0075] The welding current waveform whose features have been extracted by feature extraction unit 120 and the welding current waveform generated by welding waveform generation unit 160 may be displayed on the same screen. Since the user can confirm while comparing the welding current waveforms before and after adjustment, for example, by inputting the desired welding adjustment information (adjustment item "bead width" and adjustment amount "+1"), the user can recognize how the welding current waveform changes.

[0076] Returning to the explanation of Fig. 2, various set conditions and machine learning models are stored in storage unit 170. For example, information on features extracted by feature extraction unit 120 from the welding waveform acquired by welding waveform acquisition unit 110 is stored in storage unit 170, and feature extraction unit 120 refers to the information. In addition, welding evaluation unit 130 stores the machine learning models shown in Fig. 4 and Fig. 5 stored in storage unit 170, and evaluates welding using the machine learning models.

[0077] Furthermore, the memory unit 170 stores information related to the welding adjustment information acquired by the adjustment information acquisition unit 150, such as regulations related to adjustment items and adjustment amounts for the adjustment items. The welding waveform generation unit 160 generates a welding waveform from the waveform control parameters output using the machine learning models shown in Fig. 6 and Fig. 7 stored in the memory unit 170.

[0078] It should be noted that the items stored in memory unit 170 are not limited to these, and other data required for processing by welding waveform control device 100 may also be stored, and data may also be temporarily stored during the processing process.

[0079] [Welding waveform control method] Next, a welding waveform control method according to one embodiment of the present invention will be described in detail. Fig. 9 is a flow chart showing a welding waveform control method M100 executed by welding waveform controller 100 according to one embodiment of the present invention. As shown in Fig. 9, welding waveform control method M100 includes steps S110 to S160, and each step is executed by a processor included in welding waveform controller 100.

[0080] In step S110, the welding waveform acquisition unit 110 acquires a welding waveform during welding (welding waveform acquisition step). As a specific example, the welding waveform acquisition unit 110 acquires a welding current waveform during welding performed by the welding robot 20.

[0081] In step S120, feature extraction unit 120 extracts feature amounts based on the welding waveform acquired in step S110 (feature amount extraction step). As a specific example, feature amount extraction unit 120 extracts each of the elements (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time from the welding current waveform as feature amounts, as shown in FIG.

[0082] In step S130, the welding evaluation unit 130 evaluates the welding using a machine learning model based on the feature amount extracted in step S120 (welding evaluation step). As a specific example, as shown in Fig. 4, the welding evaluation unit 130 uses each element of (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time as input data, and outputs, using a machine learning model, evaluation results for a plurality of evaluation items related to welding, such as (A) bead width, (B) bead height, (C) undercut, and (D) spatter amount.

[0083] In the present embodiment, the welding evaluation unit 130 evaluates the welding using a machine learning model based on the feature amount, but is not limited to this. For example, the welding evaluation unit 130 may evaluate the welding using a preset calculation formula (function) or conversion table based on the welding current waveform and / or the feature amount extracted from the welding current waveform shown in Fig. 3 without using a machine learning model.

[0084] In step S140, the output unit 140 outputs the results of the evaluation in step S130 (output step). As a specific example, the output unit 140 outputs a plurality of evaluation items related to welding, such as (A) bead width, (B) bead height, (C) undercut, and (D) amount of spatter, evaluated in step S130, to a monitor or to a display screen of a tablet or dedicated terminal.

[0085] In step S150, adjustment information acquisition unit 150 acquires adjustment information for the desired welding (adjustment information acquisition step). As a specific example, when the user checks the welding result performed by welding robot 20 (welding evaluation result output in step S140) and wants to make the bead width a little wider, the user inputs, for example, an adjustment item "bead width" and an adjustment amount "+1" as adjustment information for the desired welding. Then, adjustment information acquisition unit 150 acquires the adjustment information for the welding (adjustment item "bead width" and adjustment amount "+1").

[0086] Furthermore, the user can select multiple adjustment items. For example, if the user wants to make the bead width a little wider and reduce the amount of spatter, the user can input the adjustment item "bead width" and the adjustment amount "+1", and further input the adjustment item "amount of spatter" and the adjustment amount "-1". The adjustment information acquisition unit 150 can acquire the multiple adjustment items and their corresponding adjustment amounts as adjustment information.

[0087] In step S160, the welding waveform generating unit 160 generates a welding waveform using a machine learning model based on the feature amount extracted in step S120 and the welding adjustment information acquired in step S150 (welding waveform generating step). As a specific example, as shown in Fig. 6, the welding waveform generating unit 160 uses the elements of (a) pulse current, (b) base current, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time, as well as the welding adjustment information desired by the user (adjustment item "bead width" and adjustment amount "+1") as input data, and generates a welding current waveform using the adjusted elements of (A) adjusted pulse current, (B) adjusted base current, (C) adjusted pulse interval, (D) adjusted pulse time, (E) adjusted rise time, and (F) adjusted fall time as waveform control parameters using the machine learning model.

[0088] When multiple adjustment items are acquired in step S150 with respect to the welding adjustment information, a machine learning model may be used to generate a welding waveform, with the feature amount extracted in step S120 and the adjustment information including the multiple adjustment items and their corresponding adjustment amounts acquired in step S150 as input data. The machine learning model used here may be set in advance to use adjustment information including the multiple adjustment items and their corresponding adjustment amounts as input data.

[0089] Thereafter, welding robot 20 performs welding using the welding current waveform (waveform control parameters) generated in step S160, thereby enabling welding as desired by the user.

[0090] It is also possible that the user may wish to further adjust the welding. Typically, after re-welding, the welding waveform control method M100 is repeated based on the welding waveform at the time of re-welding. However, for example, the welding current waveform may be adjusted before re-welding.

[0091] The welding current waveform generated in step S160 is displayed by a display unit (not shown) (display step), and a determination unit (not shown) determines whether the welding current waveform is to be further adjusted (welding waveform adjustment determination step). As a specific example, the display unit may output the welding current waveform generated in step S160 using the adjusted elements (A) adjusted pulse current, (B) adjusted base current, (C) adjusted pulse interval, (D) adjusted pulse time, (E) adjusted rise time, and (F) adjusted fall time as waveform control parameters to a monitor or a display screen of a tablet or dedicated terminal. Furthermore, the display unit may display the welding current waveform from which the feature amount was extracted in step S120 and the welding current waveform generated in step S160 on the same screen.

[0092] Next, if the welding current waveform generated in step S160 and displayed on a monitor or the like is to be further adjusted, the determination unit determines that the welding current waveform is to be adjusted. For example, the welding current waveform generated in step S160 is displayed on a monitor or the like to allow a user to check it, and if the user wishes to further adjust the welding current waveform, the determination unit accepts welding adjustment information from the user and determines that the welding current waveform is to be adjusted. Here, the adjustment items may be the same as or different from the previous adjustment items.

[0093] If the determination unit determines that the welding current waveform should be adjusted, the process returns to step S120, and feature extraction unit 120 extracts features based on the welding current waveform generated in step S160. Then, in step S130, welding evaluation unit 130 evaluates welding using a machine learning model based on the features extracted in step S120, and in step S140, output unit 140 outputs the result of evaluation in step S130. The evaluation of welding here is performed based on the welding current waveform during actual welding when welding is performed, or based on the welding current waveform generated in step S160 (without actually performing welding).

[0094] Next, in step S150, adjustment information acquisition unit 150 acquires desired welding adjustment information that the user wishes to further adjust, and in step S160, welding waveform generation unit 160 generates a welding current waveform using a machine learning model based on the feature amount extracted in step S120 and the welding adjustment information acquired in step S150. Then, when displaying the generated welding current waveform, the previous welding current waveform, or the welding current waveforms before that if multiple repetitions have been performed, may be displayed on the same screen.

[0095] In addition, if the user selects multiple items as adjustment items, for example, by inputting the adjustment item "bead width" with an adjustment amount of "+1" and further inputting the adjustment item "spatter amount" with an adjustment amount of "-1," the welding current waveform may be adjusted the first time to correspond to the adjustment item "bead width" and the adjustment amount of "+1" (step S160), and then the judgment unit may judge that the welding current waveform should be adjusted further (returning to step S120), and the welding current waveform may be adjusted the second time to correspond to the adjustment item "spatter amount" and the adjustment amount of "-1."

[0096] Also, for example, if the user has input the adjustment item "bead width" and adjustment amount "+3", the welding current waveform may be adjusted the first time to correspond to the adjustment item "bead width" and adjustment amount "+1" (step S160), and then the judgment unit may judge that the welding current waveform should be adjusted further (return to step S120), and the welding current waveform may be adjusted the second time to correspond to the adjustment item "bead width" and adjustment amount "+1" as in the first time, and further the welding current waveform may be adjusted the third time to correspond to the adjustment item "bead width" and adjustment amount "+1". In other words, the adjustment item "bead width" and adjustment amount "+1" are repeated three times.

[0097] Here, when the user inputs the adjustment items and adjustment amounts multiple times, the difference from the welding current waveform (evaluation result) generated immediately before may be input as the adjustment information, the accumulated amount from the original welding current waveform (evaluation result) may be input as the adjustment information, or a reference value (absolute value) such as an evaluation value may be input as the adjustment information.

[0098] As a specific example, if the spatter amount is rated as "2: high" on a five-level scale for welding evaluation, an adjustment amount of "-1 (meaning to reduce)" is input the first time to reduce the spatter amount, resulting in a rating of "3: normal." If it is desired to reduce the spatter amount even further, an adjustment amount to reduce the spatter amount can be input the second time, but here, the adjustment amount may be "-1" as the difference from the first adjustment, or "-2" as the cumulative amount. In this way, after two adjustments, the rating becomes "4: low."

[0099] Also, the user may input a target value (evaluation value) of "3: normal" the first time and a target value (evaluation value) of "4: low" the second time.

[0100] As described above, according to the welding waveform control device 100 and the welding waveform control method M100 according to an embodiment of the present invention, the feature extraction unit 120 extracts feature values ​​based on the welding current waveform acquired by the welding waveform acquisition unit 110 during welding. The welding evaluation unit 130 evaluates the welding using the feature values ​​as input data and a machine learning model with a plurality of evaluation items related to welding as output data, and the output unit 140 outputs the evaluation result to a monitor or the like. The adjustment information acquisition unit 150 acquires adjustment information (adjustment items and adjustment amounts) of welding desired by the user, and the welding waveform generation unit 160 generates a welding current waveform using a machine learning model based on the feature values ​​extracted by the feature extraction unit 120 and the welding adjustment information acquired by the adjustment information acquisition unit 150. This makes it possible to easily generate a welding current waveform for obtaining a desired welding result in a short time while evaluating the welding. As a result, the welding robot 20 performs welding desired by the user using the welding current waveform (waveform control parameters) generated by the welding waveform generation unit 160.

[0101] Furthermore, if each element extracted by the feature extraction unit 120 is used as input data for each machine learning model, the element can be confirmed, and, for example, an operator can confirm and analyze the factors and effects on the output welding evaluation results and the generated welding current waveform (waveform control parameters).

[0102] In the present embodiment, the welding waveform acquired by the welding waveform acquisition unit 110 during welding is the welding current waveform, but is not limited thereto and may be, for example, a welding voltage waveform. As the welding waveform during welding, a welding current waveform may be acquired, a welding voltage waveform may be acquired, or even both a welding current waveform and a welding voltage waveform may be acquired.

[0103] Fig. 10 is a diagram showing feature quantities extracted from the welding voltage waveform acquired by welding waveform acquisition unit 110. As shown in Fig. 10, in the case of the welding voltage waveform, feature quantity extraction unit 120 may extract each of the following elements as feature quantities from the welding voltage waveform: (a) pulse voltage, (b) base voltage, (c) pulse interval, (d) pulse time, (e) rise time, and (f) fall time. Then, welding evaluation unit 130 evaluates welding using a machine learning model with each of these elements as input data, and welding waveform generation unit 160 generates a welding voltage waveform (waveform control parameters) using the machine learning model with each of these elements as input data.

[0104] Furthermore, in this embodiment, the welding waveform control device 100 has been described as an example in which welding is performed by the welding robot 20, but is not limited thereto, and may also be applied, for example, to a case in which an operator performs welding manually. In the case of manual welding, for example, a sensor such as a gyro sensor may be provided on the welding torch, and the welding speed, torch angle, and tip-base metal (work) distance may be estimated from the measurement values ​​of the sensor, and these values ​​may be acquired by a welding condition acquisition unit as welding execution conditions, and used for evaluation of welding and generation of welding waveforms.

[0105] The above-described embodiments are intended to facilitate understanding of the present invention, and are not intended to limit the present invention. The elements of the embodiments, as well as their arrangements, materials, conditions, shapes, sizes, etc., are not limited to those shown as examples and can be changed as appropriate. In addition, configurations shown in different embodiments can be partially substituted or combined with each other. [Explanation of symbols]

[0106] 10...welding robot system, 20...welding robot, 21...welding torch, 30...teach pendant, 40...robot control device, 50...power source, 100...welding waveform control device, 110...welding waveform acquisition unit, 120...feature amount extraction unit, 130...welding evaluation unit, 140...output unit, 150...adjustment information acquisition unit, 160...welding waveform generation unit, 170...storage unit, M100...welding waveform control method, S110 to S160...each step of welding waveform control method M100

Claims

1. a welding waveform acquisition unit for acquiring a welding waveform during welding; a welding evaluation unit that evaluates the welding based on the acquired welding waveform; an output unit that outputs the evaluation result; an adjustment information acquisition unit that acquires desired welding adjustment information for the evaluation result; A welding waveform generating unit that generates a welding waveform based on the acquired welding waveform and the desired welding adjustment information. Welding waveform control device.

2. Further comprising a feature extraction unit that extracts a feature based on the acquired welding waveform, The welding evaluation unit evaluates the welding based on the extracted feature amount, The welding waveform generation unit generates a welding waveform based on the extracted feature amount and the desired welding adjustment information. The welding waveform control device according to claim 1 .

3. The welding evaluation unit evaluates the welding based on the extracted feature amount using a first machine learning model that uses the feature amount as input data and outputs an evaluation of the welding as output data. The welding waveform control device according to claim 2 .

4. The welding waveform generation unit uses a second machine learning model in which a feature amount based on a welding waveform and welding adjustment information are input data, and a waveform control parameter for generating a welding waveform is output data, to generate a welding waveform based on the extracted feature amount and the desired welding adjustment information. The welding waveform control device according to claim 2 or 3.

5. A welding waveform control method executed by a welding waveform control device that controls a welding waveform during welding, A welding waveform acquisition step for acquiring a welding waveform during welding; a welding evaluation step of evaluating the welding based on the acquired welding waveform; an output step of outputting the evaluation result; an adjustment information acquisition step of acquiring desired welding adjustment information for the evaluation result; and generating a welding waveform based on the acquired welding waveform and the desired welding adjustment information. Welding waveform control method.

Images