How to collect welding data

Abstract

To provide a method of collecting welding data that can collect collecting welding data to be used for machine learning or evaluation of welding states with a simple and inexpensive configuration.SOLUTION: A method of collecting welding data is for collecting a plurality of parameters comprising parameters that affect a welding state and representing at least a foundation shape of a target object for welding, and includes the steps of: measuring a temperature on the upstream side in a welding direction relative to a welding position on the target object; and acquiring welding data to which a value based on the temperature measured as the parameter representing the foundation shape has been input.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to a method for collecting welding data. [Background technology]

[0002] As a technique for improving welding quality, for example, Patent Document 1 describes a technique in which physical quantities related to arc welding, such as the appearance of the weld bead, bead reinforcement height, and bead width, obtained by processing image data, are learned through machine learning, along with arc welding conditions, such as welding speed and extension length, and the arc welding conditions are adjusted based on the physical quantities obtained from the image data to perform automatic welding. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6126174 Summary of the Invention [Problem to be solved by the invention]

[0004] Laser displacement meters are sometimes used to precisely measure the shapes of the welding object (base material) and weld beads. However, laser displacement meters are expensive, which increases the cost of collecting welding data used to measure the shapes of the welding object, weld beads, etc.

[0005] The present disclosure has been made in consideration of such problems, and provides a welding data collection method that can collect welding data to be used for machine learning or evaluation of welding conditions using a simple and inexpensive configuration. [Means for solving the problem]

[0006] According to one aspect of the present disclosure, a method for collecting welding data is a method for collecting welding data consisting of a plurality of parameters that affect the welding state, including at least a parameter that represents a base shape of a welding object, the method including the steps of measuring the temperature of the welding object as the parameter that represents the base shape, and acquiring the welding data into which a value based on the measured temperature is input as the parameter that represents the base shape. [Effects of the Invention]

[0007] According to the welding data collection method of the present disclosure, welding data to be used for machine learning or evaluation of welding conditions can be collected using a simple and inexpensive configuration. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a schematic diagram illustrating an overall configuration of a welding data collection system according to an embodiment of the present disclosure. [Figure 2] FIG. 10 is a diagram illustrating an example of a temperature measurement value according to an embodiment of the present disclosure. [Figure 3] 1 is a flowchart illustrating an example of a method for collecting welding data according to an embodiment of the present disclosure. [Figure 4] FIG. 2 is a diagram illustrating an example of welding data according to an embodiment of the present disclosure. [Figure 5] FIG. 1 is a first diagram illustrating an example of a machine learning model constructed using learning data according to an embodiment of the present disclosure. [Figure 6] FIG. 2 is a second diagram showing an example of a machine learning model constructed using learning data according to an embodiment of the present disclosure. [Figure 7] FIG. 1 is a diagram illustrating a functional configuration of a welding support device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, a welding data collection method according to an embodiment of the present disclosure will be described with reference to FIGS.

[0010] (Overall configuration of welding data collection system) FIG. 1 is a schematic diagram showing the overall configuration of a welding data collection system according to an embodiment of the present disclosure. As shown in FIG. 1, a collection system 1 according to this embodiment includes a learning device 10, a welding device 20, a data logger 30, and a welding support device 90.

[0011] Welding device 20 is equipped with an operation panel on which instruments and devices such as switches and levers for adjusting various parameters that affect the welding state are mounted. A welder welds object 50 using welding rod 21 having electrode 210 while adjusting each parameter on the operation panel of the welding device. These parameters include, for example, welding current, welding voltage, and extension length of electrode 210. The welding state is an abnormality level that indicates the presence or absence of welding defects or signs of such defects.

[0012] Data logger 30 collects welding data consisting of a plurality of parameters measured by sensors provided at various locations, such as welding device 20 and near the welding site, as learning data and evaluation data. Data logger 30 collects learning data consisting of parameters such as the welding current and welding voltage measured by an ammeter and voltmeter provided in welding device 20, and the temperature measured by radiation thermometer 40. Data logger 30 also collects welding data to be evaluated (evaluation data) when evaluating the welding state.

[0013] Radiation thermometer 40 is placed at measurement position R2, which is a position a predetermined distance W away from welding position R1 (position of electrode 210) upstream in the welding direction. Radiation thermometer 40 measures the temperatures of welding object 50 and weld bead 51 at measurement position R2.

[0014] The learning device 10 performs machine learning based on the learning data collected by the data logger 30 and constructs a learning model for evaluating the welding condition. For example, the learning device 10 constructs, based on the welding data, an evaluation model for evaluating the degree of abnormality in the welding condition, a defect estimation model for estimating the location and type of a welding defect, and the like.

[0015] The welding support device 90 monitors the welding state based on the welding data (evaluation data) acquired by the data logger 30, and displays the current welding state on the display device 91 to support the welding work of the welder.

[0016] (Regarding the bottom topographical trend) It is known that the occurrence of welding defects is likely influenced by unevenness in the topography of the substrate. For this reason, conventional technology has been to measure the substrate shape using a laser displacement meter, and include this measurement data in the learning data used for machine learning. However, as mentioned above, laser displacement meters are expensive, which increases the cost of collecting learning data.

[0017] FIG. 2 is a diagram illustrating an example of a temperature measurement value according to an embodiment of the present disclosure. Figure 2 is a graph showing the transition of preheat temperature in the path where a welding defect occurs. The horizontal axis of Figure 2 represents welding position R1 of the welding object 50, and the vertical axis represents the preheat temperature at measurement position R2. Note that, for example, when welding a circular structure such as a pipe while rotating it, the welding position may be represented by the rotation angle of the structure. Position Rn represents the position where a welding defect occurs. The welding defect was detected by non-destructive testing after welding.

[0018] As shown in Figure 2, the preheat temperature is unstable just before the welding defect location Rn. The radiation thermometer 40 may measure temperatures that vary if the surface at the measurement location is uneven. Therefore, it is assumed that the preheat temperature fluctuation is due to the unevenness of the surface of the weld bead 51 formed in the previous pass, i.e., the underlying topography.

[0019] Furthermore, the information required for machine learning is not absolute values ​​but trends. In other words, it is possible to learn whether or not the substrate is uneven from trend data of preheating temperatures obtained from an inexpensive radiation thermometer 40, rather than from precise measurement data using an expensive laser displacement meter.

[0020] Based on this knowledge, the data logger 30 according to this embodiment acquires learning data in which the measurement values ​​of the radiation thermometer 40 are input as the values ​​of a parameter representing the preheat temperature at measurement position R2 and a parameter representing the base shape at measurement position R2. The parameter representing the base shape is a feature that can detect the presence or absence of unevenness in the base topography, such as the measured value of the preheat temperature or the magnitude of variation in the preheat temperature.

[0021] It is also possible to directly evaluate the presence or absence of defects in the substrate topography based on parameters that represent the substrate shape. Therefore, data logger 30 may acquire welding data that includes parameters that represent the substrate shape as evaluation data, rather than learning data for the welding state. Welding support device 90 evaluates the presence or absence of defects (unevenness) in the substrate topography based on this evaluation data.

[0022] Furthermore, because the preheat temperature measurement position R2 is upstream of the welding position R1, any preheat temperature disturbances (irregularities in the base topography) are detected before a welding defect actually occurs. In other words, by learning learning data including these preheat temperature disturbances, a learning model can be constructed that can detect signs of a welding defect before welding at a location with an irregular base topography. By using this learning model, it is possible to take action, such as stopping the welding work, before a welding defect actually occurs. Note that it is desirable to set the distance W between the welding position R1 and the measurement position R2 to a distance that allows the welder to take appropriate action, such as stopping the welding work, when such a sign of a welding defect is detected.

[0023] (How welding data is collected) FIG. 3 is a flowchart illustrating an example method for collecting welding data according to an embodiment of the present disclosure. FIG. 4 is a diagram illustrating an example of welding data according to an embodiment of the present disclosure. Here, with reference to Figures 3 and 4, we will explain the process flow for collecting welding data (learning data or evaluation data) in which the measurement values ​​obtained by the data logger 30 from the radiation thermometer 40 are input as values ​​for two parameters, namely, the preheating temperature and the bottom topography trend.

[0024] First, radiation thermometer 40 measures the temperatures of welding object 50 and weld bead 51 at measurement position R2 (step S10).

[0025] 4, data logger 30 inputs the measurement value acquired from radiation thermometer 40 into the "preheating temperature" parameter of welding data T (step S11). Data logger 30 also inputs the feature quantity based on the measurement value acquired from radiation thermometer 40 into the "bottom topography trend" parameter of welding data T (step S12).

[0026] In addition, the data logger 30 acquires and records the welding data T, which further includes measurement values ​​and feature quantities measured by sensors (such as an ammeter and a voltmeter) not shown in the figure of the welding device 20 for each of the other parameters of the welding data T (such as the welding current and the welding voltage) (step S13).

[0027] The data logger 30 collects welding data T by repeatedly executing the series of processes shown in FIG.

[0028] (Regarding the use of learning data) The welding data T (hereinafter also referred to as learning data T) collected by the data logger 30 is used when the learning device 10 learns the machine learning model.

[0029] FIG. 5 is a first diagram illustrating an example of a machine learning model constructed using learning data according to an embodiment of the present disclosure. For example, as shown in FIG. 5, the learning device 10 constructs an evaluation model M1 that is a model that learns learning data T (normal data P) collected during a period when the welding state is normal, and that evaluates the degree of abnormality of welding data X obtained during evaluation.

[0030] During evaluation, from among the normal data P included in the evaluation model M1, the normal data Pk1 closest to the welding data X (e.g., the 10th closest) is selected, and the distance D between this k1th normal data Pk1 and the welding data X is calculated as the abnormality degree of the welding data X. If the distance D (abnormality degree) exceeds a predetermined threshold, it is predicted that a welding defect may occur.

[0031] By using the evaluation model M1 trained using the above-mentioned learning data, when there is a large variation in the preheating temperature, i.e., when the base topography is uneven, the degree of abnormality becomes high and it is possible to predict the occurrence of welding defects.

[0032] FIG. 6 is a second diagram illustrating an example of a machine learning model constructed using learning data according to an embodiment of the present disclosure. 6, the learning device 10 may perform supervised learning based on the learning data and the positions and types of welding defects detected by inspection to construct a defect estimation model M2 that estimates the positions and types of welding defects. When the welding data acquired during evaluation is input as an explanatory variable, the defect estimation model M2 outputs the positions and types of welding defects as objective variables.

[0033] During evaluation, a heat map showing the location and type of welding defects may be generated based on the estimation results of defect estimation model M2, as shown in Figure 6. Weld defects 1, 2, 3, 4, ... each represent a different type of welding defect (e.g., planar defect, volumetric defect, porosity, slag inclusion, etc.). The vertical axis of the heat map represents the weld layer and pass, and the horizontal axis represents the position in the welding direction. For example, when welding a ring-shaped structure such as a pipe while rotating it, the position in the welding direction may be represented by the angle of the structure.

[0034] By using the defect estimation model M2 trained using the above-mentioned learning data, it is possible to predict the occurrence of welding defects caused by unevenness in the underlying topography from the trend of the preheating temperature.

[0035] (Regarding the use of evaluation data) Furthermore, as described above, data logger 30 may collect welding data T not as learning data but as evaluation data. The evaluation data collected by data logger 30 is used, for example, by welding support device 90 to evaluate the welding state.

[0036] FIG. 7 is a diagram illustrating a functional configuration of a welding support device according to an embodiment of the present disclosure. As shown in FIG. 7, welding support device 90 includes an acquisition unit 901, a determination unit 902, and an output unit 903.

[0037] The acquisition unit 901 acquires welding data T (hereinafter also referred to as evaluation data T) from the data logger 30.

[0038] The determination unit 902 evaluates the welding state of the welding object 50 based on the welding data. Specifically, the determination unit 902 evaluates whether or not there is a defect in the lower topography based on the "lower topography trend (preheating temperature trend)" parameter included in the evaluation data T. As described above, unevenness in the lower topography tends to cause variations in the preheating temperature. For this reason, the determination unit 902 determines that there is a defect (unevenness) in the lower topography when, for example, the magnitude of variation in the preheating temperature exceeds a predetermined threshold.

[0039] The output unit 903 outputs (displays) the determination result of the determination unit 902 to the display device 91 and presents it to the welder. The welder refers to the determination result indicating a defect in the base topography and takes appropriate action, such as temporarily suspending welding or performing work to resolve the defect in the base topography.

[0040] In another embodiment, the determination unit 902 may evaluate the welding condition using the evaluation data T acquired from the data logger 30 and a learning model learned by the learning device 10. For example, the determination unit 902 evaluates the degree of abnormality in the welding condition using the evaluation data T and an evaluation model M1 that evaluates the degree of abnormality in the welding condition. The determination unit 902 also estimates the type and position of a welding defect using the evaluation data T and a defect estimation model M2.

[0041] (Action, effect) As described above, the method for collecting learning data according to this embodiment includes the steps of measuring the temperature upstream of the welding position R1 of the welding object 50, and acquiring welding data T into which a value based on the measured temperature is input as a parameter representing the base shape.

[0042] In this way, it is possible to obtain welding data T in which the temperature measurement data is input as the value of a parameter representing the substrate shape. This makes it possible to collect welding data T including parameters representing the substrate shape with a simple and inexpensive configuration that does not use an expensive laser displacement sensor. This reduces the cost of collecting welding data T.

[0043] The temperature of the welding object is measured by a radiation thermometer 40 .

[0044] In this way, the temperature of the welding object can be measured without contact.

[0045] The radiation thermometer 40 is placed at a measurement position R2 upstream of the welding position R1 in the welding direction.

[0046] In this way, it is possible to collect welding data T including parameters that can detect the presence of unevenness in the base topography before the occurrence of a welding defect. By using a learning model trained based on such welding data T, it is possible to predict abnormalities and welding defects caused by the unevenness in the base topography before welding is performed on a location with unevenness in the base topography. Furthermore, by using the welding data T as evaluation data, it is possible to detect defects in the base topography before welding is performed on a location with unevenness in the base topography.

[0047] The welding data T is learning data T for a learning model that evaluates the welding state.

[0048] In this way, it is possible to collect learning data T for learning the welding state including the substrate shape with a simple and inexpensive configuration.

[0049] The learning model is constructed by learning learning data T collected during a period when the welding condition is normal, and is an evaluation model M1 that evaluates the degree of abnormality of the welding data obtained during evaluation.

[0050] In this way, by performing learning based on the learning data T collected with a simple and inexpensive configuration, the cost for constructing the evaluation model M1 can be reduced. Furthermore, by using the evaluation model M1 trained with the learning data T, it is possible to evaluate the presence or absence of unevenness in the base topography from the trend of the preheating temperature, by reflecting this in the degree of abnormality.

[0051] In addition, the learning model is a model constructed by learning the learning data and the location and type of welding defects detected by inspection, and is a defect estimation model in which the welding data obtained during evaluation is used as an explanatory variable and the location and type of welding defects are used as target variables.

[0052] In this way, by performing learning based on the training data T collected with a simple and inexpensive configuration, the cost of constructing the defect estimation model M2 can be reduced. Furthermore, by using the defect estimation model M2 trained with the training data T, the location and type of welding defects caused by unevenness in the base topography can be estimated from the trend of the preheating temperature.

[0053] As described above, several embodiments according to the present disclosure have been described, but all of these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents as defined in the claims, as well as in the scope and spirit of the invention.

[0054] <Additional Notes> The welding data collection method described in the above embodiment can be understood, for example, as follows.

[0055] (1) According to a first aspect of the present disclosure, a method for collecting welding data is a method for collecting welding data T consisting of a plurality of parameters that affect the welding state, including at least a parameter representing the base shape of the object to be welded (50), and includes the steps of measuring the temperature upstream of the welding position of the object to be welded (50) in the welding direction as one of the parameters representing the base shape, and acquiring welding data T into which a value based on the measured temperature is input as the parameter representing the base shape.

[0056] In this way, it is possible to obtain learning data T in which values ​​based on the measurement data of the radiation thermometer 40 are input as values ​​of two different parameters, namely, the preheating temperature and the base topography. This makes it possible to collect learning data T with a simple and inexpensive configuration that omits an expensive laser displacement sensor. This reduces the cost of collecting learning data T. Furthermore, by measuring the temperature upstream of the welding position, it is possible to collect welding data T that includes parameters that can detect the presence of unevenness in the base topography before a welding defect occurs.

[0057] (2) According to a second aspect of the present disclosure, in the collection method according to the first aspect, the temperature of the welding object is measured by a radiation thermometer.

[0058] In this way, the temperature of the welding object can be measured without contact.

[0059] (3) According to a third aspect of the present disclosure, in the collection method according to the first or second aspect, the welding data T is learning data T for a learning model that evaluates the welding state.

[0060] In this way, it is possible to collect learning data T for learning the welding state including the substrate shape with a simple and inexpensive configuration.

[0061] (4) According to a fourth aspect of the present disclosure, in the collection method relating to the third aspect, the learning model is a model constructed by learning learning data T collected during a period when the welding condition is normal, and is an evaluation model M1 that evaluates the degree of abnormality of the welding data obtained during evaluation.

[0062] In this way, by performing learning based on the learning data T collected with a simple and inexpensive configuration, the cost for constructing the evaluation model M1 can be reduced. Furthermore, by using the evaluation model M1 trained with the learning data T, it is possible to evaluate the presence or absence of unevenness in the base topography from the trend of the preheating temperature, by reflecting this in the degree of abnormality.

[0063] (5) According to a fifth aspect of the present disclosure, in the collection method related to the third aspect, the learning model is a model constructed by learning the learning data T and the type of welding defect detected by inspection, and is a defect estimation model M2 in which the welding data obtained during evaluation is the explanatory variable and the type of welding defect is the target variable.

[0064] In this way, by performing learning based on the training data T collected with a simple and inexpensive configuration, the cost of constructing the defect estimation model M2 can be reduced. Furthermore, by using the defect estimation model M2 trained with the training data T, the location and type of welding defects caused by unevenness in the base topography can be estimated from the trend of the preheating temperature. [Explanation of symbols]

[0065] 1. Welding data collection system 10 Learning Device 20 Welding equipment 21 Welding rod 210 Electrode 30 Data Logger 40 Radiation thermometer 90 Welding support equipment 91 Display device

Claims

1. A method for collecting welding data consisting of a plurality of parameters that affect the welding state, including at least a parameter that represents the shape of a substrate to be welded, comprising: measuring a temperature upstream of a welding position of the welding object in a welding direction as one of the parameters representing the base shape; acquiring the welding data into which a value based on the measured temperature is input as a parameter representing the base shape; and The temperature of the welding object is measured by a radiation thermometer. Collection method.

2. The welding data is learning data for a learning model for evaluating the welding state. The collection method of claim 1 .

3. The learning model is a model constructed by learning learning data collected during a period when the welding state is normal, and is an evaluation model for evaluating the degree of abnormality of welding data acquired during evaluation. The collection method according to claim 2 .

4. the learning model is a model constructed by learning the learning data and the types of welding defects detected by inspection, and is a defect estimation model in which the welding data acquired during evaluation is used as an explanatory variable and the type of welding defect is used as a target variable. The collection method according to claim 2 .

Images