Method for predicting weld property, method for generating prediction model, and prediction model

Abstract

A welded part characteristic prediction method for predicting the characteristics of a welded part 5 obtained through resistance spot welding in which a current is passed between two electrodes 3, 4 sandwiching a plate assembly obtained by superposing two or more metal plates, the method including: a step for acquiring electrical information outputted during the resistance spot welding, the electrical information including at least one of the current flowing between the two electrodes 3, 4, the voltage between the two electrodes 3, 4, the resistance between the two electrodes 3, 4, or the amount of heat generated between the two electrodes 3, 4 in the resistance spot welding; and a step for predicting the characteristics of the welded part 5 on the basis of the electrical information.

Description

[Technical Field]

[0001] The present disclosure relates to a method for predicting the properties of a weld obtained by resistance spot welding, a method for generating a predictive model of the properties of a weld, and a predictive model of the properties of a weld. [Background technology]

[0002] Resistance spot welding is performed to assemble the bodies of automobiles and other vehicles. Resistance spot welding is performed at several thousand locations on a single vehicle body. Resistance spot welding is a welding method in which two or more steel sheets are overlapped, clamped between a pair of upper and lower welding electrodes, and pressure is applied while an electric current is passed between the welding electrodes to form a nugget of a predetermined size between the steel sheets, thereby obtaining a welded joint. The joint strength of a weld made by resistance spot welding is determined by the nugget diameter. In welding that requires high joint strength, such as welding of automobile parts, it is important to form a nugget of a predetermined diameter or larger between the steel sheets. A method for manufacturing a spot-welded joint with a nugget diameter of the required size is known (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2005-262259 Summary of the Invention [Problem to be solved by the invention]

[0004] To select resistance spot welding conditions capable of producing spot-welded joints with the required nugget diameter, experiments are conducted under various conditions for welding steel plates, and the cross sections of the resulting welded joints are observed to measure the nugget diameter. The more conditions under which experiments are conducted, the greater the number of welded joints for which nugget diameters must be measured. The time required to measure the nugget diameter of a welded joint decreases the efficiency of the process of selecting resistance spot welding conditions. There is a need to improve the efficiency of the process of selecting resistance spot welding conditions. In particular, in a stack of three or more metal plates, where the thickness ratio (the thickness of the thinnest metal plate divided by the total thickness of the stack) is 5 or greater, it is difficult to form a nugget between the thinnest and thickest metal plates. Patent Document 1 discloses a welding method that stabilizes nugget formation by applying current and pressure in multiple stages. However, the increased number of welding parameters further reduces the efficiency of the process of selecting welding conditions. Therefore, when assembling sheets in which three or more metal sheets are overlapped and the sheet thickness ratio is 5 or more, it is necessary to further improve the efficiency of the work of selecting resistance spot welding conditions.

[0005] In view of the above, an object of the present disclosure is to provide a weld property prediction method, a prediction model generation method, and a prediction model that enable efficient selection of resistance spot welding conditions. [Means for solving the problem]

[0006] In order to achieve the above object, a method for determining welding conditions for resistance spot welding according to the present disclosure is as follows.

[0007] [1] A method for predicting the properties of a welded joint of a set of two or more overlapping metal plates, obtained by resistance spot welding in which a current is passed between two electrodes sandwiching the set of two or more overlapping metal plates, acquiring electrical information output during resistance spot welding, the electrical information including at least one of a current flowing between the two electrodes, a voltage between the two electrodes, a resistance between the two electrodes, or an amount of heat generated between the two electrodes; a step of predicting the properties of a welded portion of the plate assembly formed by overlapping the two or more metal plates based on the electrical information; A method for predicting weld properties, comprising:

[0008] [2] The method for predicting the welded portion characteristics described in [1] above, wherein in the step of predicting the welded portion characteristics, the electrical information is input into a prediction model of the welded portion characteristics to obtain a prediction result of the welded portion characteristics output from the prediction model.

[0009] [3] The method for predicting welded portion characteristics described in [2] above, further comprising a step of generating the prediction model by performing learning using the electrical information and the analysis results of the welded portion characteristics as learning data.

[0010] [4] A method for predicting welded joint characteristics described in any one of [1] to [3] above, wherein in the step of obtaining predicted results of the welded joint characteristics, a predicted result of at least one of the welded joint's nugget diameter, tensile shear strength, cross tensile strength, or fracture strength by mechanical peel test is obtained as the welded joint characteristics.

[0011] [5] The method for predicting welded portion characteristics according to any one of [1] to [4] above, wherein, in the step of acquiring the electrical information, a total amount of heat generated from the start of energization to the end of energization of the resistance spot welding is acquired as the electrical information.

[0012] [6] The method for predicting weld characteristics according to [5] above, wherein in the step of acquiring electrical information, the resistance between the two electrodes at the end of current flow is acquired as the electrical information.

[0013] [7] The method for predicting welded portion characteristics according to the above [5] or [6], wherein in the step of acquiring the electrical information, the amount of heat generated during a part of the period from the start of energization to the end of energization of the resistance spot welding is acquired as the electrical information.

[0014] [8] The resistance spot welding is performed on a plate set including three or more overlapping metal plates including at least a first metal plate, a second metal plate, and a third metal plate; The plate thickness ratio, which is the value obtained by dividing the total plate thickness of the plate set by the plate thickness of the thinnest metal plate in the plate set, is 5 or more. The method for predicting welded joint characteristics according to any one of [1] to [4] above.

[0015] [9] The method for predicting weld characteristics according to the above [8], wherein in the step of acquiring the electrical information, a total amount of heat generated from the start of energization to the end of energization of the resistance spot welding is acquired as the electrical information.

[0016]

[10] The method for predicting weld characteristics according to [9] above, wherein in the step of acquiring electrical information, the resistance between the two electrodes at the end of current flow is acquired as the electrical information.

[0017]

[11] The resistance spot welding includes a first stage in which a first current is applied and a second stage in which a second current is applied;

[11] The method for predicting welded portion characteristics according to [9] or

[10] above, wherein, in the step of acquiring the electrical information, the amount of heat generated during the first stage of the period from the start of energization to the end of energization of the resistance spot welding is acquired as the electrical information.

[0018]

[12] A method for generating a model for predicting the characteristics of a welded portion of a sheet set formed by overlapping two or more metal sheets, obtained by resistance spot welding in which a current is passed between two electrodes sandwiching the sheet set formed by overlapping two or more metal sheets, acquiring electrical information output during resistance spot welding, the electrical information including at least one of a current flowing between the two electrodes, a voltage between the two electrodes, a resistance between the two electrodes, or an amount of heat generated between the two electrodes; a step of acquiring an analysis result of characteristics of the weld when resistance spot welding is performed on the sheet set formed by overlapping the two or more metal sheets; a step of performing machine learning based on learning data that associates the electrical information with an analysis result of the characteristics of the weld when resistance spot welding is performed on the sheet assembly formed by overlapping the two or more metal sheets, and generating a model that predicts the characteristics of the weld of the sheet assembly formed by overlapping the two or more metal sheets; A method for generating a predictive model, comprising:

[0019]

[13] A predictive model for predicting the characteristics of a weld obtained by resistance spot welding, generated using the predictive model generation method described in

[12] above. [Effects of the Invention]

[0020] According to the present disclosure, a method for predicting weld characteristics, a method for generating a prediction model, and a prediction model that enable efficient selection of resistance spot welding conditions are provided. [Brief explanation of the drawings]

[0021] [Figure 1] FIG. 1 is a schematic diagram illustrating an overview of resistance spot welding. [Figure 2] FIG. 1 is a block diagram illustrating a configuration example of a prediction system according to the present disclosure. [Figure 3A] 1 is a graph showing an example of a change over time in inter-electrode resistance value in resistance spot welding. [Figure 3B] 1 is a graph showing an example of a change over time in the cumulative heat generation amount in resistance spot welding. [Figure 4] 1 is a flowchart illustrating an example of a procedure for generating a prediction model. [Figure 5] 1 is a flowchart illustrating an example of a procedure for a method for predicting welded portion characteristics. [Figure 6] FIG. 1 is a cross-sectional view showing an example of a welded portion of a plate assembly in which three metal plates are stacked. [Figure 7] 10 is a graph showing an example of a pattern in which a current flowing between electrodes is divided into two stages. [Figure 8A] FIG. 1 is a cross-sectional view showing an example of a welded portion when a first-stage current is passed through a plate assembly in which three metal plates are stacked. [Figure 8B] FIG. 10 is a cross-sectional view showing an example of a welded portion when a second-stage current is passed through a plate assembly in which three metal plates are stacked. [Figure 9] 1 is a graph showing an example of a correlation between total heat generation amount and nugget diameter. [Figure 10] 1 is a graph showing an example of a correlation between an initial heat generation amount and a nugget diameter. DETAILED DESCRIPTION OF THE INVENTION

[0022] Hereinafter, embodiments of the weld property prediction method, prediction model generation method, and prediction model according to the present disclosure will be described with reference to the drawings. The drawings are schematic and may differ from the actual product. Furthermore, the following embodiments exemplify an apparatus or method for embodying the technical idea of ​​the present disclosure, and are not intended to limit the configuration to that described below. In other words, the technical idea of ​​the present disclosure can be modified in various ways within the technical scope described in the claims.

[0023] The weld property prediction method according to the present disclosure predicts the properties of a weld obtained by resistance spot welding. Resistance spot welding, performed to obtain a weld that is the target of prediction by the method according to the present disclosure, is a method of joining metal sheets 1 and 2 by sandwiching a pair of overlapping metal sheets 1 and 2 between electrodes 3 and 4 and applying pressure while passing an electric current between the electrodes 3 and 4, as shown in FIG. 1 . When a current flows between the electrodes 3 and 4, the temperatures of the metal sheets 1 and 2 increase due to heat generated by the electrical resistance of the metal sheets 1 and 2 and heat generated by the contact resistance between the metal sheets 1 and 2. When current flows between the electrodes 3 and 4, the hot portions of the metal sheets 1 and 2 melt and solidify after the current flow is stopped, forming a weld 5 that joins the metal sheets 1 and 2. The weld 5 can have a disk-like shape with the axis of rotation being the line connecting the electrodes 3 and 4. The weld 5 is also called a "nugget."

[0024] The joint strength of the weld 5 obtained by performing resistance spot welding is determined by the area of ​​the weld 5 joining the metal plates 1 and 2. In other words, the joint strength of the weld 5 is determined by the size of the weld 5 when viewed from above. The size of the weld 5 when viewed from above may be expressed as the diameter d of the disk-shaped weld 5. The diameter d of the disk-shaped weld 5 is also referred to as the nugget diameter. When high joint strength is required for automobile parts, etc., it is important that the weld 5 be formed so that the nugget diameter is equal to or greater than a predetermined diameter.

[0025] Weld 5 is located between metal plate 1 and metal plate 2. To confirm that the nugget diameter of weld 5 is equal to or greater than a predetermined diameter, a test is conducted in which metal plate 1 and metal plate 2 are actually welded together, a sample is taken from the weld joint obtained in the test, and the nugget diameter is measured by cross-sectional observation. To determine the welding conditions that will result in a nugget diameter of weld 5 equal to or greater than the predetermined diameter, the test and cross-sectional observation must be repeated while changing the welding conditions. However, cross-sectional observation requires a great deal of man-hours and cost.

[0026] The joint strength of the weld 5 is expressed as the tensile shear strength or cross tensile strength of the weld 5. When high joint strength is required for automobile parts, etc., it is important that the weld 5 is formed so that the tensile shear strength or cross tensile strength of the weld 5 is increased. In order to confirm the tensile shear strength or cross tensile strength of the weld 5, a test must be conducted in which the metal plates 1 and 2 are actually welded together, and a fracture test must be conducted in which a load is applied to the welded joint obtained in the test. In order to determine the welding conditions that will achieve the required joint strength of the weld 5, it is necessary to repeat the test and fracture test while changing the welding conditions. However, the fracture test requires a great deal of man-hours and cost.

[0027] Therefore, in order to reduce the man-hours and costs required for determining welding conditions and to improve the efficiency of selecting welding conditions, it is necessary to predict the nugget diameter of a weld 5 without performing cross-sectional observation and to predict the strength of a weld 5 without performing a fracture test. According to the weld property prediction method of the present disclosure, the properties of a weld 5, including the nugget diameter or strength of a weld 5, are predicted without performing cross-sectional observation or a fracture test of a welded joint obtained by testing. As a result, the selection of welding conditions is made more efficient.

[0028] (Configuration example of prediction system 100) As shown in FIG. 2, a prediction system 100 according to an embodiment of the present disclosure includes a prediction model generation device 10, a prediction device 20, a welding device 30, and an analysis device 40.

[0029] The welding device 30 performs resistance spot welding, joining two or more stacked metal plates, such as metal plates 1 and 2 in FIG. 1, by sandwiching them between two electrodes 3 and 4 (see FIG. 1) and applying pressure while passing current between the two electrodes 3 and 4. The welding device 30 is configured to control both the welding pressure and the welding current flowing between the electrodes during welding. The welding device 30 may be of various types, such as a stationary type or a robot gun. The power source of the welding device may be either a DC power source or an AC power source. When the power source is an AC power source, processing such as ignoring calculations at points where V = 0 or obtaining a moving average to prevent the resistance from becoming infinite is performed to prevent the resistance from becoming zero. The electrodes 3 and 4 of the welding device 30 may have a shape with curved tips as exemplified in FIG. 1, but are not limited to this and may have various other shapes. The welding device 30 outputs electrical information during resistance spot welding. The electrical information output from the welding device 30 during resistance spot welding includes at least one of the current flowing between the two electrodes when performing resistance spot welding, the voltage between the two electrodes when performing resistance spot welding, the resistance between the two electrodes when performing resistance spot welding, or the amount of heat generated between the two electrodes when performing resistance spot welding. Hereinafter, the electrical information output during resistance spot welding will also be referred to as electrical information during resistance spot welding.

[0030] A sheet assembly may be formed by stacking two or more steel plates. When one or more of the two or more steel plates constituting the sheet assembly are high-tensile steel plates of 590 MPa or higher, the work of confirming the welding condition through analysis is time-consuming. Therefore, by selecting welding conditions for a sheet assembly including high-tensile steel plates using the method of the present disclosure, the effect of the present disclosure in improving the efficiency of the work of selecting welding conditions is significant. Furthermore, when the strength difference between the thinnest and thickest metal plates of the two or more steel plates constituting the sheet assembly is 590 MPa or higher, the work of confirming the welding condition through analysis is even more time-consuming. Therefore, by selecting welding conditions for a sheet assembly including metal plates with a strength difference of 590 MPa or higher using the method of the present disclosure, the effect of the present disclosure in improving the efficiency of the work of selecting welding conditions is even greater.

[0031] The number of metal plates constituting the plate assembly to be joined by resistance spot welding is not limited to two and may be three or more. The two or more metal plates to be joined by resistance spot welding may be steel plates. At least one of the two or more metal plates to be joined by resistance spot welding may be a steel plate having a plating layer. Two or more metal plates may be steel plates having a plating layer. The steel plate having a plating layer may have the plating layer on only one side or on both sides. The steel plate having a plating layer may be, for example, a zinc-based plated steel plate.

[0032] The analysis device 40 analyzes the properties of the welded portion of the plate assembly after resistance spot welding is performed by the welding device 30, and outputs the analysis results of the welded portion properties. The analysis device 40 may include a cross-section observation device or a non-destructive inspection device that measures the nugget diameter of the welded portion. The analysis device 40 may include a fracture testing device that measures the bonding strength of the welded portion. The welded portion properties include at least one of the nugget diameter of the welded portion, tensile shear strength, cross tensile strength, or fracture strength obtained by a mechanical peel test.

[0033] The prediction model generation device 10 includes a data acquisition unit 12, a database 14, and a model generation unit 16. The data acquisition unit 12 acquires electrical information during resistance spot welding from a welding device 30 in a test in which resistance spot welding is actually performed on a plate assembly consisting of two or more overlapping metal plates to weld the plate assembly. The data acquisition unit 12 acquires analysis results of weld characteristics of sample welded joints obtained in the welding test from an analysis device 40. The data acquisition unit 12 stores data in a database 14 that associates the electrical information during resistance spot welding in the welding test with the analysis results of the weld characteristics of the sample welded joints obtained in the welding test. The model generation unit 16 performs learning using the data stored in the database 14 as learning data. The model generation unit 16 performs learning to generate a model that predicts weld characteristics. The model that predicts weld characteristics is configured to output predicted results of weld characteristics when resistance spot welding is performed using an operation specified by the electrical information when electrical information during resistance spot welding is input. The model generation unit 16 outputs the generated model to a prediction device 20.

[0034] Prediction device 20 uses the model acquired from prediction model generation device 10 as prediction model 22. Prediction device 20 acquires electrical information during resistance spot welding when a welding test is performed with welding device 30, and inputs the information to prediction model 22. Prediction device 20 acquires the predicted results of the welded portion characteristics output from prediction model 22, and outputs the results to the outside.

[0035] The predictive model generation device 10, the prediction device 20, the welding device 30, or the analysis device 40 are connected to each other so that they can communicate with each other. The predictive model generation device 10, the prediction device 20, the welding device 30, or the analysis device 40 may be provided with a communication interface based on a wired or wireless communication standard. For example, the wireless communication standard may include a cellular phone communication standard such as 3G, 4G, or 5G. Furthermore, for example, the wireless communication standard may include IEEE 802.11 or Bluetooth (registered trademark). The communication interface may support one or more of these communication standards. The communication interface is not limited to these examples and may communicate with other devices or input and output data based on various standards. The predictive model generation device 10, the prediction device 20, the welding device 30, or the analysis device 40 may be connected via a network or directly (for example, peer-to-peer (P2P)).

[0036] The prediction device 20 may be communicatively connected to an external device so as to transmit the prediction results of the weld characteristics to the external device. The prediction device 20 may include an output device that outputs the prediction results of the weld characteristics. The prediction device 20 may include a display device for displaying the prediction results of the weld characteristics as the output device. The display device may include, for example, an LCD (Liquid Crystal Display), an organic EL (Electro-Luminescence) display or an inorganic EL display, or a PDP (Plasma Display Panel). The display device is not limited to these displays and may include various other types of displays.

[0037] The prediction model generation device 10 or the prediction device 20 may be configured to include at least one processor, such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The prediction model generation device 10 or the prediction device 20 may be configured with one processor or multiple processors. The processor constituting the prediction model generation device 10 or the prediction device 20 may realize the functions of the prediction model generation device 10 or the prediction device 20 by reading and executing a program stored in a storage unit described below.

[0038] The prediction model generation device 10 or the prediction device 20 may include a storage unit. The storage unit stores various types of information or data. The storage unit may store, for example, a program executed in the prediction model generation device 10 or the prediction device 20, or data or processing results used in processing executed in the prediction model generation device 10 or the prediction device 20. The storage unit may also function as a work memory for the prediction model generation device 10 or the prediction device 20. The storage unit may include, but is not limited to, a semiconductor memory. For example, the storage unit may be configured as an internal memory of a processor used as the prediction model generation device 10 or the prediction device 20, or as a hard disk drive (HDD) accessible from the prediction model generation device 10 or the prediction device 20. The storage unit may be configured as a non-transitory readable medium. The storage unit may be configured integrally with the prediction model generation device 10 or the prediction device 20, or may be configured separately from the prediction model generation device 10 or the prediction device 20.

[0039] The prediction system 100 does not need to include the predictive model generation device 10. If the prediction system 100 does not include the predictive model generation device 10, the prediction device 20 acquires the predictive model 22 from an external device. The prediction system 100 does not need to include the welding device 30. If the prediction system 100 does not include the welding device 30, the predictive model generation device 10 or the prediction device 20 acquires electrical information during resistance spot welding in a welding experiment from an external device that performs the welding. The prediction system 100 does not need to include the analysis device 40. If the prediction system 100 does not include the analysis device 40, the predictive model generation device 10 acquires analysis results of the weld properties of welded joint samples obtained in a welding experiment from an external device that performs the analysis.

[0040] (Example of operation of prediction system 100) An example of the operation of the prediction system 100 will now be described in detail.

[0041] The data acquisition unit 12 of the prediction model generation device 10 acquires electrical information during resistance spot welding performed in the welding experiment from the welding device 30. The data acquisition unit 12 acquires from the analysis device 40 the analysis results of the weld characteristics of the welded joint samples obtained in the welding experiment.

[0042] The data acquisition unit 12 selects one or more pieces of performance data from the electrical information during resistance spot welding and stores them in the database 14. The performance data of the electrical information during resistance spot welding includes at least one of the current flowing between the two electrodes or the voltage applied between the two electrodes when resistance spot welding is being performed, the resistance between the two electrodes when resistance spot welding is being performed, or the amount of heat generated between the two electrodes when resistance spot welding is being performed.

[0043] The data acquisition unit 12 selects one or more pieces of performance data from the analysis results of the weld characteristics and stores them in the database 14. The performance data of the weld characteristics includes at least one of the nugget diameter, tensile shear strength, and cross tensile strength of the weld 5 (see FIG. 1). The analysis results of the weld characteristics are information obtained by offline testing in the analysis device 40.

[0044] The data acquisition unit 12 stores the actual data of electrical information during resistance spot welding and the actual data of welded portion characteristics in the database 14 together with additional information such as a welding control number so that the data can be associated with each other. The actual data of electrical information during resistance spot welding and the actual data of welded portion characteristics are associated by the additional information such as the welding control number and stored in the database 14 as a set of data sets. One data set corresponding to one welding condition of a welding experiment is stored in the database 14. The number of data sets used to generate the prediction model 22 is preferably 100 or more, more preferably 200 or more, and even more preferably 300 or more.

[0045] The model generation unit 16 uses one or more pieces of actual data selected from the electrical information during resistance spot welding among the data sets stored in the database 14 as input actual data, and performs machine learning using the input actual data to generate a trained prediction model 22. The machine learning method performed by the model generation unit 16 may be a known learning method. Any machine learning method may be used as long as the trained prediction model 22 provides sufficient prediction accuracy for weld characteristics for practical use. For example, a known machine learning method using a neural network, such as deep learning, a convolutional neural network (CNN), or a recurrent neural network (RNN), may be used. Other methods may include regression tree learning, support vector regression, or Gaussian processes. An ensemble model combining multiple models may also be used. After the prediction model 22 is generated by performing machine learning, it may be appropriately updated by re-learning using the latest training data.

[0046] <Actual data on electrical information during resistance spot welding> As described above, in the prediction system 100 according to this embodiment, one or more pieces of actual data are selected from the electrical information during resistance spot welding and used to predict the weld characteristics. The one or more pieces of actual data selected from the electrical information during resistance spot welding include, for example, the welding current I, the interelectrode voltage V, the interelectrode resistance R, or the heat generation amount Q. The welding current I is the value of the current flowing between the two electrodes 3 and 4 (see FIG. 1 ) during resistance spot welding. The interelectrode voltage V is the voltage applied between the two electrodes 3 and 4 during resistance spot welding. The interelectrode resistance R is the electrical resistance between the two electrodes 3 and 4 and is calculated as R=V / I using the interelectrode voltage V and the welding current I. The heat generation amount Q is the amount of heat generated between the two electrodes 3 and 4 and is calculated as Q=(I·R)^2 / (r·t^2) using the welding current I, the interelectrode resistance R, and the resistivity r and thickness t of the metal sheets constituting the sheet assembly. When the metal plate is a steel plate, the resistivity r is the specific resistance value of pure iron at 1200°C.

[0047] During resistance spot welding, the resistance of the metal plate changes as the metal plate melts. As a result, as illustrated in FIG. 3A, the inter-electrode resistance R changes over time during resistance spot welding. Furthermore, as illustrated in FIG. 3B, the cumulative value of heat generation increases over time during resistance spot welding. In the graphs of FIGS. 3A and 3B, the horizontal axis represents the welding time of the resistance spot welding. The vertical axis of the graph of FIG. 3A represents the inter-electrode resistance R. The vertical axis of the graph of FIG. 3B represents the cumulative heat generation, which is the cumulative value of the heat generation between the electrodes.

[0048] The symbols indicating specific times on the horizontal axes of FIGS. 3A and 3B are defined as follows: Tm: The time when the inter-electrode resistance R reaches its maximum value (Rmax) Ts: The time that has elapsed since the start of current application for resistance spot welding Tf: Time when current flow through the resistance spot welding is completed Tml: The intermediate time between the time (Tm) when the inter-electrode resistance R reaches its maximum value (Rmax) and the time (Tf) when the current flow ends, calculated as Tm + (Tf - Tm) / 2

[0049] The symbols indicating specific resistance values ​​on the vertical axis of FIG. 3A are defined as follows: Rfirst: The value of the inter-electrode resistance R when a predetermined time (Ts) has elapsed since the start of resistance spot welding current Rmax: Maximum interelectrode resistance R Rfm: The value of the inter-electrode resistance R at half the time (Tm) when the inter-electrode resistance R reached its maximum value (Rmax) Rlast: The value of the interelectrode resistance R at the end of resistance spot welding. Rml: The value of the interelectrode resistance R at the midpoint (Tml) between the time (Tm) when the interelectrode resistance R reaches its maximum value (Rmax) and the time (Tf) when the current flow ends.

[0050] The symbols indicating specific heat values ​​on the vertical axis of FIG. 3B are defined as follows: Qm: Cumulative heat generation up to the time (Tm) when the inter-electrode resistance R reaches its maximum value (Rmax) Qi: The cumulative heat generated from the start of current application to the specified time (Ts) Qt: Cumulative heat generation from the start of current application to the end of current application in resistance spot welding Qi is also called the initial heat release, and Qt is also called the total heat release.

[0051] The values ​​indicated by the above-described symbols identify the actual data of electrical information during resistance spot welding. In other words, the actual data of electrical information during resistance spot welding includes the values ​​indicated by the above-described symbols. Among the actual data of electrical information during resistance spot welding, the total calorific value Qt has been found to have a significant effect on weld characteristics. For example, in the examples described below, it has been confirmed that the total calorific value Qt correlates with the nugget diameter. Therefore, among the actual data of electrical information during resistance spot welding, the total calorific value Qt may be used as the actual data used to generate the prediction model 22 and as the actual data input to the prediction model 22 to predict the weld characteristics.

[0052] It has also been found that the initial heat generation amount Qi significantly affects the nugget growth process at the beginning of current application during resistance spot welding. In other words, it has been found that the initial heat generation amount Qi, among the actual data of electrical information during resistance spot welding, significantly affects the weld characteristics. The initial heat generation amount Qi is the amount of heat generated during a portion of the period from the start of current application to the end of current application during resistance spot welding. The predetermined time Ts defining the initial heat generation amount Qi may be set to, for example, 200 ms (milliseconds). The initial heat generation amount Qi may be calculated by excluding the amount of heat generated during a very short period, for example, 10 ms, at the beginning of welding after the start of current application during resistance spot welding. For example, in the examples described below, it has been confirmed that the initial heat generation amount Qi and the nugget diameter are correlated. Therefore, the initial heat generation amount Qi may be used as the actual data of electrical information during resistance spot welding used to generate the prediction model 22 and as the actual data input to the prediction model 22 to predict the weld characteristics. Using the initial heat generation amount Qi improves prediction accuracy.

[0053] Furthermore, it has been found that various values ​​of interelectrode resistance R (Rfirst, Rfm, Rmax, Rml, or Rlast, or Rmean, which is the average value of interelectrode resistance R over the entire period from the start to the end of welding) among the actual electrical information data during resistance spot welding have a significant effect on the weld characteristics. The value of interelectrode resistance R is significantly affected by the current diameter, which in turn is affected by the nugget diameter. For example, the value of interelectrode resistance R at the end of welding (Rlast) correlates with the final nugget diameter. Therefore, the value of interelectrode resistance R at the end of welding (Rlast) may be used to predict the nugget diameter of the weld.

[0054] <Welded part characteristics> Examples of weld properties include the nugget diameter d of the weld 5 (see FIG. 1 ), cross tensile strength, shear tensile strength, and fracture strength by a mechanical peel test. Weld properties are measured by taking test specimens from a welded joint obtained by resistance spot welding a sheet assembly of two or more overlapping metal sheets. Among the weld properties, the nugget diameter may be measured by the method described in JIS Z3140 or by non-destructive testing such as ultrasonic testing or eddy current testing. The cross tensile strength may be measured by the method described in JIS Z3137. The shear tensile strength may be measured by the method described in JIS Z3136. The fracture strength by a mechanical peel test may be measured by the method described in ISO 14270.

[0055] <Welding conditions> The welding conditions for resistance spot welding, which are the targets of weld property prediction in the prediction system 100 according to this embodiment, are not particularly limited. For example, the welding conditions may be set so that a constant current flows from the start to the end of the resistance spot welding. The welding conditions may also be set so that the period from the start to the end of the resistance spot welding is divided into a first stage and a second stage, with different welding conditions for the first stage and the second stage, resulting in two-stage welding. In particular, when welding a sheet assembly in which three or more metal sheets are stacked together and the sheet thickness ratio, which is the thickness of the thinnest metal sheet divided by the total sheet thickness of the sheet assembly, is 5 or greater, it is preferable to perform two-stage welding under the following conditions.

[0056] In the first stage of welding, the welding pressure P1 (kN) is preferably set to satisfy the following formula (1) in relation to the thickness tm of the thinnest metal plate among the multiple metal plates: The thickness of the thinnest metal plate corresponds to the thickness (mm) of the upper steel plate 6 in Figure 6. 0.8tm≦P1≦5tm ………(1)

[0057] If the welding pressure P1 in the first stage is 5 tm (kN) or more, the welding pressure becomes too high, the heat generated by contact resistance decreases, and a nugget does not form between the upper steel plate 6 and the middle steel plate 7. On the other hand, if the welding pressure P1 is 0.8 tm or less, the contact resistance between the electrode tip and the upper steel plate 6 increases, making it easier for sparks to occur and for expulsion to occur between the upper steel plate 6 and the middle steel plate 7.

[0058] In the first stage of welding, the current application time T1 (ms) is preferably set so as to satisfy the following formula (2). 30≦T1≦120 ………(2)

[0059] If the current application time T1 is 30 ms or less, the current application time is too short, and a nugget of the desired size is not formed between the upper steel sheet 6 and the middle steel sheet 7. On the other hand, if the current application time T1 is longer than 120 ms, expulsion occurs.

[0060] In the first-stage welding, the welding current I1 (kA) is preferably set to satisfy the following equation (3) in relation to the thickness tm of the thinnest metal plate among the multiple metal plates: The thinnest plate thickness corresponds to the thickness (mm) of the upper steel plate 6 in Figure 6. 3tm+5≦I1 ………(3)

[0061] If the welding current I1 in the first stage welding is (3tm+5) or less, the heat generated by contact resistance cannot be effectively utilized, and a nugget will not be formed between the upper steel sheet 6 and the middle steel sheet 7.

[0062] For this reason, in the first stage of welding, it is preferable to set the welding pressure P1, welding current I1, or current flow time T1 so as to satisfy the above-mentioned equations (1), (2), and (3) in order to form a nugget of the desired size between the upper steel plate 6 and the middle steel plate 7.

[0063] In the second stage welding, the welding pressure P2 (kN) is preferably set so as to satisfy the following formula (4) in relation to the welding pressure P1 in the first stage welding. P1≦P2≦10P1 ………(4)

[0064] Moreover, the second-stage welding current I2 (kA) is preferably set so as to satisfy the following formula (5) in relation to the first-stage welding current I1. 0.5≦I2≦I1 ………(5)

[0065] Furthermore, it is preferable that the second-stage welding current application time T2 (ms) is set so as to satisfy the following formula (6) in relation to the first-stage welding current application time T1. T1≦T2≦10T1 ………(6)

[0066] If the second-stage welding conditions are outside the above-mentioned ranges, it becomes difficult to prevent expulsion or obtain the desired nugget diameter. Furthermore, excessively increasing the welding pressure can result in problems such as large heat marks or lifting. When performing two-stage welding, it is desirable to set the predetermined time (Ts) in the electrical information performance data during the resistance spot welding described above to the time when the first stage ends and the second stage begins.

[0067] When selecting welding conditions for performing welding with two-stage current application as described above, the number of combinations of conditions increases. Therefore, by applying the prediction system 100 and prediction method according to this embodiment to selecting welding conditions for performing welding with two-stage current application, the efficiency of the work of selecting welding conditions is improved.

[0068] Furthermore, the amount of heat generated during a first stage of resistance spot welding may be acquired as electrical information during resistance spot welding. By using the amount of heat generated during the first stage of resistance spot welding as electrical information during resistance spot welding, the prediction accuracy of weld characteristics is improved.

[0069] The prediction system 100 and prediction method according to the present embodiment may be applied not only to selecting welding conditions for the welding methods described above, but also to selecting welding conditions for various other welding methods. The prediction system 100 and prediction method according to the present embodiment may be applied to selecting welding conditions for, for example, single-stage welding in which the current value and welding force are constant, multi-stage welding in which the set values ​​of the current value or welding force are changed midway, or adaptive control in which the current value is controlled according to a reference heat quantity. Furthermore, the prediction system 100 and prediction method according to the present embodiment may be applied to selecting welding conditions for a method that includes post-welding after main welding to form a weld.

[0070] <Flowchart example> In the prediction system 100 according to this embodiment, the prediction model 22 may be generated by executing a flowchart including the steps illustrated in FIG.

[0071] The welding device 30 performs a welding test on the plate assembly for which the welding conditions for resistance spot welding are to be determined (step S1). The welding conditions for the welding test may be set as appropriate.

[0072] The data acquisition unit 12 of the predictive model generation device 10 acquires electrical information during resistance spot welding performed by the welding device 30 in the welding test (step S2). The data acquisition unit 12 of the predictive model generation device 10 also acquires analysis results of the weld characteristics for the weld joint sample obtained by the welding test (step S3). The analysis results of the weld characteristics are obtained by the analysis device 40 performing offline analysis of the weld joint sample obtained by the welding test. The data acquisition unit 12 stores data in the database 14 that associates the electrical information during the resistance spot welding with the analysis results of the weld characteristics.

[0073] The model generation unit 16 of the prediction model generation device 10 performs learning using the data stored in the database 14 as learning data, and generates a prediction model 22 of the weld characteristics (step S4). After completing the procedure of step S4, the prediction system 100 ends the execution of the flowchart in FIG.

[0074] In the prediction system 100 according to this embodiment, a flowchart including the procedure illustrated in FIG. 5 may be executed to determine welding conditions through welding tests.

[0075] Test conditions for conducting a welding test on the plate assembly for which the welding conditions for resistance spot welding are to be determined are set (step S11). The test conditions may be set by a person who will conduct the welding test, etc.

[0076] Prediction device 20 acquires electrical information from welding device 30 during resistance spot welding performed by welding device 30 in a welding test (step S12). Prediction device 20 predicts the weld characteristics of the welded joint obtained by the welding test based on the electrical information during resistance spot welding (step S13). Prediction device 20 may input the electrical information during resistance spot welding to prediction model 22 and acquire the predicted results of the weld characteristics output from prediction model 22.

[0077] It is determined whether the prediction result of the weld property by prediction device 20 is satisfactory (step S14). The determination of the prediction result of the weld property may be made by the person who carried out the welding test, or may be made by prediction device 20 or an external device that has acquired the prediction result from prediction device 20. If the prediction result of the weld property is not satisfactory (step S14: NO), the process returns to the test condition setting procedure in step S11 and the test is repeated.

[0078] If the predicted results of the weld characteristics are good (step S14: YES), the welded joint obtained in the test is actually analyzed, and it is determined whether the analysis results are good (step S15). The determination of the analysis results of the weld characteristics may be made by the person who carried out the welding test, or may be made by a device such as analysis device 40. If the analysis results of the weld characteristics are not good (step S15: NO), the process returns to the test condition setting procedure in step S11 and the test is repeated.

[0079] If the analysis result of the welded portion characteristics is good (step S15: YES), the test conditions under which good welded portion characteristics are obtained are determined as the welding conditions (step S16). After completing the procedure of step S16, the prediction system 100 ends the execution of the flowchart in FIG.

[0080] (Small summary) As described above, the prediction system 100 according to the present disclosure predicts the welded joint characteristics of a welded joint based on actual electrical information obtained during resistance spot welding when a welding test is performed on a sheet assembly for which welding conditions are to be determined, without actually analyzing the welded joint obtained through the welding test. Being able to predict welded joint characteristics without actual analysis makes it easy to increase the number of welding tests with different welding conditions. This improves the efficiency of the task of selecting welding conditions suitable for achieving a predetermined nugget diameter and strength when the target sheet assembly is welded.

[0081] (Example) Specific examples are described below. In these examples, a servomotor-driven single-phase AC resistance spot welder is used as the welding device 30. The spot welder is equipped with a chromium copper DR-type electrode with a tip diameter of 6 mm and a curvature radius of 40 mm. In these examples, welding conditions are determined for a plate assembly of three overlapping steel plates, as illustrated in FIG. 6. The plate assembly for which welding conditions are determined includes an upper steel plate 6, a middle steel plate 7, and a lower steel plate 8. The upper steel plate 6 is also referred to as the first metal plate. The middle steel plate 7 is also referred to as the second metal plate. The lower steel plate 8 is also referred to as the third metal plate. In these examples, the upper steel plate 6 and the middle steel plate 7 contact each other, and the middle steel plate 7 and the lower steel plate 8 contact each other. The upper steel plate 6 is a steel plate with a tensile strength of 270 MPa and a thickness of 0.7 mm. Steel plates with a tensile strength of 1470 MPa and a thickness of 1.6 mm are used as the middle steel plate 7 and the bottom steel plate 8. That is, the plate combination for which the welding conditions are determined in this example is configured so that the first metal plate is thinner than the second and third metal plates, and the second and third metal plates have the same thickness.

[0082] The above-described welding test of the plate assembly was carried out using the above-described welding device 30. In this example, the welding conditions for the welding test were set to two stages of current conduction, in which different welding currents were passed between the electrodes during a first stage represented by time T1 and a second stage represented by time T2, as illustrated in FIG. 7. The horizontal axis of FIG. 7 represents the current flow time of resistance spot welding. The vertical axis represents the current passed between the electrodes. The welding current passed between the electrodes during the first stage is represented as I1. The welding current passed between the electrodes during the second stage is represented as I2.

[0083] As illustrated in FIG. 8A , current application during the first stage causes the temperature to rise at the contact surface between the upper steel plate 6 and the middle steel plate 7, which is thinner than the middle steel plate 7 and the lower steel plate 8, earlier than at the contact surface between the middle steel plate 7 and the lower steel plate 8, resulting in melting of the steel plate and forming a first weld 51. As illustrated in FIG. 8B , current application during the second stage also causes the temperature to rise at the contact surface between the middle steel plate 7 and the lower steel plate 8, resulting in melting of the steel plate and forming a second weld 52. As a result, as illustrated in FIG. 6 , one weld 5 is formed, joining the three steel plates. The nugget diameter of the weld 5 is measured as a nugget diameter d1 at the contact surface between the upper steel plate 6 and the middle steel plate 7 and a nugget diameter d2 at the contact surface between the middle steel plate 7 and the lower steel plate 8, as shown in FIG. 6 . The nugget diameters d1 and d2 are the diameters of the weld 5 when the steel plates constituting the sheet assembly are viewed in plan. When the welded portion 5 is formed in a disk shape with the normal line of each steel plate constituting the sheet assembly as the rotation axis, the nugget diameters d1 and d2 are measured on a cross section of the sheet assembly taken so as to pass through the rotation axis.

[0084] Specifically, the welding conditions were set as follows: electrode pressure 3-5 kN (kilonewtons), welding current I1 5-13 kA (kiloamperes), and current application time T1 60 ms (milliseconds) during the first stage. Also, the welding conditions were set as follows: electrode pressure 3-5 kN, welding current I2 5-10 kA, and current application time T2 360 ms during the second stage.

[0085] The electrode pressure and welding current were each changed within the above-mentioned ranges to set 180 combinations of welding conditions. Resistance spot welding was performed on the plate pairs for which the welding conditions were determined in this example, applying each of the 180 welding conditions, and 180 welded joints were created.

[0086] In this example, nugget diameter was analyzed as a weld property of 180 welded joints. Specifically, the nugget diameter was measured by cutting the weld of the welded joint obtained by welding, etching the cross section, and observing it with an optical microscope. As the nugget diameter, the nugget diameter d1 between the upper steel plate 6 and the middle steel plate 7 and the nugget diameter d2 between the middle steel plate 7 and the lower steel plate 8, as shown in FIG. 6, were measured.

[0087] The data acquisition unit 12 of the predictive model generation device 10 acquires performance data of electrical information during resistance spot welding using each of the 180 welding conditions and performance data of nugget diameters of the 180 welded joints. The data acquisition unit 12 associates the performance data of electrical information and the performance data of nugget diameters during resistance spot welding corresponding to each welding condition and stores them in the database 14 of the predictive model generation device 10.

[0088] The model generation unit 16 of the prediction model generation device 10 acquires data associating actual data on electrical information during resistance spot welding with actual data on nugget diameter from the database 14. The model generation unit 16 performs machine learning using the acquired data as learning data to generate a prediction model 22 that outputs a predicted nugget diameter when actual data on electrical information during resistance spot welding is input. Ridge regression, a type of regression model, was used as the machine learning model. As described above, it has been found that the total heat generation amount Qt, among actual data on electrical information during resistance spot welding, has a significant impact on weld characteristics. For example, as shown in FIG. 9, the total heat generation amount Qt correlates with nugget diameters d1 and d2. The horizontal axis of the graph in FIG. 9 represents the total heat generation amount Qt. The vertical axis represents the nugget diameter. Based on the correlation between the total heat generation amount Qt and the nugget diameter, in this embodiment, the total heat generation amount Qt was selected as actual data on electrical information during resistance spot welding. Furthermore, Qm was also selected. Furthermore, as actual data of electrical information during resistance spot welding, Rfirst, Rfm, Rmax, Rml, Rlast, and Rmean of the inter-electrode resistance values ​​were further selected.

[0089] Using the prediction model 22 generated by the prediction model generation device 10 as described above, the prediction device 20 can predict the nugget diameter of a welded joint obtained in a welding test performed under new welding conditions without observing the cross section of the welded joint. In this example, 50 new welding conditions were set and 50 welded joints were created. When the results of predicting the nugget diameter of the welded joints using the prediction model 22 were compared with the results of actually measuring the nugget diameter of the welded joints, the nugget diameter d1 between the upper steel plate 6 and the middle steel plate 7 was predicted with an error of ±9%. Furthermore, the nugget diameter d2 between the middle steel plate 7 and the lower steel plate 8 was predicted with an error of ±2%.

[0090] As described above, it has been found that the initial heat generation amount Qi, which is part of the actual electrical information data during resistance spot welding, has a significant effect on weld characteristics. For example, as shown in FIG. 10, there is a correlation between the initial heat generation amount Qi and the nugget diameter d1. The horizontal axis of the graph in FIG. 10 represents the initial heat generation amount Qi, and the vertical axis represents the nugget diameter. Based on the correlation between the initial heat generation amount Qi and the nugget diameter, as another example, a prediction model 22 was generated by performing learning in which the initial heat generation amount Qi was further added to the training data as actual electrical information data during resistance spot welding. The initial heat generation amount Qi is assumed to be the cumulative heat generation amount from the start of current application up to 60 ms (milliseconds). When using the prediction model 22 generated by adding the initial heat generation amount Qi, the nugget diameter d1 between the upper steel sheet 6 and the middle steel sheet 7 was predicted with an error of ±7%. Furthermore, the nugget diameter d2 between the middle steel sheet 7 and the lower steel sheet 8 was predicted with an error of ±2%. The prediction accuracy of the nugget diameter d1 between the upper steel plate 6 and the middle steel plate 7 was improved by adopting the initial heat generation amount Qi as actual data to be input into the prediction model 22. In other words, the prediction accuracy of the nugget diameter at the contact surface between the thin steel plate and the thick steel plate was improved by adopting the initial heat generation amount Qi as actual data to be input into the prediction model 22.

[0091] As described in the examples, the prediction system 100 according to the present disclosure predicts weld characteristics, such as nugget diameter, with high accuracy based on actual electrical information data during resistance spot welding. High-accuracy prediction of nugget diameter eliminates the need to expose a cross section of a welded joint created in a welding test and actually measure the nugget diameter. This reduces the labor and costs required for the process of exposing a cross section of a welded joint and actually measuring the nugget diameter. As a result, the number of welding conditions set in a welding test can be increased, allowing for efficient selection of welding conditions.

[0092] The prediction system 100 and prediction method according to the present disclosure can be executed on a sheet assembly having two or more overlapping metal sheets to improve the efficiency of the work of selecting welding conditions for the sheet assembly having two or more overlapping metal sheets. Furthermore, the prediction system 100 and prediction method according to the present disclosure can be executed on a sheet assembly having three or more overlapping metal sheets to improve the efficiency of the work of selecting welding conditions for the sheet assembly having three or more overlapping metal sheets. The work of selecting welding conditions for a sheet assembly having three or more overlapping metal sheets is more difficult than the work of selecting welding conditions for a sheet assembly having two overlapping metal sheets. Therefore, the effect of improving the efficiency of the work of selecting welding conditions can be further enhanced by executing the prediction system 100 and prediction method according to the present disclosure on a sheet assembly having three or more overlapping metal sheets.

[0093] In the above-described example, the thickness of the upper steel sheet 6 was 0.7 mm, and the thickness of the middle steel sheet 7 was 1.6 mm. In other words, the thickness ratio, calculated by dividing the total thickness of the sheet assembly by the thickness of the thinnest metal sheet, was approximately 5.6. It is known that the larger the thickness ratio of a sheet assembly to be resistance spot welded, the more difficult it is to form a weld with the required nugget diameter at the contact surface between the thin and thick steel sheets. It is particularly difficult to determine welding conditions for resistance spot welding sheet assemblies with a thickness ratio greater than 5. The prediction system 100 according to the present disclosure can accurately predict weld characteristics for sheet assemblies in which steel sheets are stacked in combinations with even larger thickness ratios, particularly those with a thickness ratio greater than 5, thereby improving the efficiency of the work of determining welding conditions.

[0094] Although the embodiments of the present disclosure have been described based on the drawings and examples, it should be noted that those skilled in the art could make various modifications or alterations based on the present disclosure. Therefore, it should be noted that these modifications and alterations are included within the scope of the present disclosure. For example, the functions included in each component or step can be rearranged so as not to cause logical inconsistencies, and multiple components or steps can be combined or divided into one. The embodiments of the present disclosure can also be realized as a program executed by a processor included in an apparatus or a storage medium on which a program is recorded. It should be understood that these are also included within the scope of the present disclosure. [Explanation of symbols]

[0095] 100 Prediction System 1, 2 metal plate 3, 4 electrodes 5 Welded section (51: first welded section, 52: second welded section) 6 Upper steel plate 7 Medium steel plate 8 Lower steel plate 10 Prediction model generation device (12: Data acquisition unit, 14: Database, 16: Model generation unit) 20 Prediction Device (22: Prediction Model) 30 Welding equipment 40 Analyzer

Claims

1. A method for predicting the characteristics of a welded portion of a plate assembly made up of three or more overlapping metal plates, including at least a first metal plate, a second metal plate, and a third metal plate, obtained by resistance spot welding in which an electric current is passed between two electrodes that sandwich the plate assembly, the method comprising: The resistance spot welding includes a first stage of applying a first current between the two electrodes that sandwich the sheet pair with a first pressure, and a second stage of applying a second current between the two electrodes that sandwich the sheet pair with a second pressure, acquiring electrical information output during resistance spot welding, the electrical information including at least one of a current flowing between the two electrodes, a voltage between the two electrodes, a resistance between the two electrodes, or an amount of heat generated between the two electrodes; predicting the properties of the welded portion of the plate assembly formed by overlapping the three or more metal plates based on the electrical information; Including, a heat generation amount during the first stage of a period from the start of energization to the end of energization of the resistance spot welding, as the electrical information, in the step of acquiring the electrical information.

2. 2. The weld property prediction method according to claim 1, wherein in the step of predicting the properties of the weld, the electrical information is input into a prediction model of the properties of the weld, and a prediction result of the properties of the weld output from the prediction model is obtained.

3. The method for predicting welded portion characteristics according to claim 2 , further comprising the step of generating the prediction model by performing learning using the electrical information and the analysis results of the welded portion characteristics as learning data.

4. 2. The weld property prediction method according to claim 1, wherein in the step of obtaining a predicted result of the property of the weld, a predicted result of at least one of a nugget diameter of the weld, a tensile shear strength, a cross tensile strength, or a fracture strength by a mechanical peel test is obtained as the property of the weld.

5. 5. The method for predicting welded portion characteristics according to claim 1, wherein, in the step of acquiring the electrical information, a total amount of heat generated from a start of energization to an end of energization of the resistance spot welding is acquired as the electrical information.

6. The method for predicting welded portion characteristics according to claim 5 , wherein in the step of acquiring electrical information, a resistance between the two electrodes at the end of current flow is acquired as the electrical information.

7. 6. The method for predicting welded portion characteristics according to claim 5, wherein, in the step of acquiring the electrical information, a heat generation amount during a part of a period from the start of energization to the end of energization of the resistance spot welding is acquired as the electrical information.

8. The thickness ratio, which is the value obtained by dividing the total thickness of the plate assembly by the thickness of the thinnest metal plate among the three or more plate assembly, is 5 or more. The method for predicting weld characteristics according to any one of claims 1 to 4.

9. 9. The method for predicting welded portion characteristics according to claim 8, wherein, in the step of acquiring electrical information, a total amount of heat generated from the start of energization to the end of energization of the resistance spot welding is acquired as the electrical information.

10. The method for predicting welded portion characteristics according to claim 9 , wherein in the step of acquiring electrical information, a resistance at the end of current flow between the two electrodes is acquired as the electrical information.

11. A method for predicting weld characteristics described in any one of claims 1 to 4, wherein the time for which the first current is passed in the first stage is 30 ms or more and 120 ms or less.

12. A method for generating a model for predicting the characteristics of a welded portion of a plate assembly including three or more overlapping metal plates, the plate assembly including at least a first metal plate, a second metal plate, and a third metal plate, obtained by resistance spot welding in which an electric current is passed between two electrodes sandwiching the plate assembly, the method comprising: The resistance spot welding includes a first stage of applying a first current between the two electrodes that sandwich the sheet pair with a first pressure, and a second stage of applying a second current between the two electrodes that sandwich the sheet pair with a second pressure, acquiring electrical information output during resistance spot welding, the electrical information including at least one of a current flowing between the two electrodes, a voltage between the two electrodes, a resistance between the two electrodes, or an amount of heat generated between the two electrodes; acquiring an analysis result of characteristics of the weld when resistance spot welding is performed on the sheet assembly including the three or more overlapping metal sheets; a step of performing machine learning based on learning data that associates the electrical information with an analysis result of the characteristics of the weld when resistance spot welding is performed on the plate assembly formed by overlapping the two or more metal plates, and generating a model that predicts the characteristics of the weld of the plate assembly formed by overlapping the two or more metal plates; Including, a heat generation amount during the first stage of a period from the start of energization to the end of energization of the resistance spot welding, as the electrical information, in the step of acquiring the electrical information.

13. A predictive model generation method as described in Claim 12, wherein the time for which the first current is flowed in the first stage is not less than 30 ms and not more than 120 ms.

Images