Prediction method and program

Abstract

The present invention provides a prediction method that can predict a plastic strain distribution, deformation distribution, or residual stress distribution in a short time and with high accuracy. The prediction method according to the present invention is for predicting a plastic strain distribution, residual stress distribution, or deformation of an object, and includes a step for outputting predictive output data corresponding to a plastic strain distribution from predictive input data that includes heating conditions by using a machine learning model that has been trained using teaching data, which includes input data for learning that includes heating conditions and output data for learning that corresponds to a plastic strain distribution calculated from the heating conditions using a numerical analysis method.

Description

[Technical Field]

[0001] The present invention relates to a prediction method and program for predicting plastic strain distribution (intrinsic strain distribution), residual stress distribution, or deformation. [Background technology]

[0002] Numerical analysis using thermo-elastic-plastic analysis is commonly used to calculate residual stresses generated by welding. Using thermo-elastic-plastic analysis, it is possible to consider the welding conditions when welding the target steel material in a digital space. However, with thermo-elastic-plastic analysis, it is necessary to input time-series data of the temperature distribution that changes from moment to moment, from heating to the end of cooling. This results in a huge amount of calculation and long analysis times. Furthermore, when analyzing an object with a complex shape, the analysis time becomes even longer. The inherent strain method is known as a method for shortening the analysis time (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-144425 Summary of the Invention [Problem to be solved by the invention]

[0004] However, when the deformations obtained by the inherent strain method are compared with those obtained by the thermo-elastic-plastic analysis method, the analysis results often deviate.Furthermore, when the deformations obtained by the inherent strain method are compared with those of welded components, the deformations often deviate. The present invention has been made in view of the above circumstances, and provides a prediction method that can predict plastic strain distribution, deformation distribution, or residual stress distribution in a short time with high accuracy. [Means for solving the problem]

[0005] The present invention provides a prediction method for predicting the plastic strain distribution (inherent strain distribution), residual stress distribution, or deformation of a target object, the prediction method including a step of outputting prediction output data corresponding to the plastic strain distribution from prediction input data including heating conditions using a machine learning model trained with teacher data including learning input data including heating conditions and learning output data corresponding to the plastic strain distribution (inherent strain distribution) calculated from the heating conditions using a numerical analysis method. [Effects of the Invention]

[0006] According to the present invention, it is possible to predict the plastic strain distribution (inherent strain distribution), deformation or residual stress distribution in a short time with high accuracy. Furthermore, it is possible to predict the plastic strain distribution, deformation or residual stress distribution of a complex target object in a short time. The prediction method of the present invention does not require the tedious task of creating an element mesh, thereby reducing the workload of the analyst. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is an explanatory diagram of a prediction method according to an embodiment of the present invention. [Figure 2] FIG. 10 is an explanatory diagram of geometric conditions showing the heating position on the input side. [Figure 3] FIG. 10 is an explanatory diagram of geometric conditions showing the heating position on the input side. [Figure 4] FIG. 10 is an explanatory diagram of input items required for fillet welding. [Figure 5] This is the relationship between inherent deformation and inherent strain. [Figure 6] FIG. 1 is a schematic diagram of an analytical model of a target object used in a thermo-elastic-plastic analysis. [Figure 7] (a) is the plastic strain distribution in the x direction created from the results of the thermo-elastic-plastic analysis, and (b) is the plastic strain distribution in the x direction created from the prediction output data. [Figure 8](a) is the plastic strain distribution in the x direction created from the results of the thermo-elastic-plastic analysis, and (b) is the plastic strain distribution in the x direction created from the prediction output data. [Figure 9] (a) is the plastic strain distribution in the y direction created from the results of the thermo-elastic-plastic analysis, and (b) is the plastic strain distribution in the y direction created from the prediction output data. [Figure 10] 6(a) to 6(d) are graphs comparing the inherent deformation calculated using the relational expression in FIG. 5 with the inherent deformation calculated using thermo-elasto-plastic analysis. [Figure 11] (a) is the plastic strain distribution in the x direction created from the results of the thermo-elastic-plastic analysis, and (b) is the plastic strain distribution in the x direction created from the prediction output data. [Figure 12] (a) is the plastic strain distribution in the y direction created from the results of the thermo-elastic-plastic analysis, and (b) is the plastic strain distribution in the y direction created from the prediction output data. [Figure 13] 6(a) to 6(d) are graphs comparing the inherent deformation calculated using the relational expression in FIG. 5 with the inherent deformation calculated using thermo-elasto-plastic analysis. [Figure 14] (a) is the plastic strain distribution in the x direction created from the results of the thermo-elastic-plastic analysis, and (b) is the plastic strain distribution in the x direction created from the output data for this prediction. [Figure 15] (a) is the residual stress distribution in the x direction created from the results of the thermo-elastic-plastic analysis, and (b) is the residual stress distribution in the x direction created from the data calculated by elastically analyzing the prediction output data. [Figure 16] Graphs (a) and (b) compare the inherent deformation calculated using the relational expression in FIG. 5 with that calculated using thermo-elasto-plastic analysis. [Figure 17] This is the angular distortion distribution along the heating direction created from the prediction output data. [Figure 18] This is the angular distortion distribution along the heating direction created from the prediction output data. [Figure 19] This is the angular distortion distribution along the heating direction created from the prediction output data. [Figure 20] This is the angular distortion distribution along the heating direction created from the prediction output data. [Figure 21] This is a distribution of transverse shrinkage along the heating direction created from the prediction output data. [Figure 22] This is a distribution of transverse shrinkage along the heating direction created from the prediction output data. [Figure 23] This is a distribution of transverse shrinkage along the heating direction created from the prediction output data. [Figure 24] This is a distribution of transverse shrinkage along the heating direction created from the prediction output data. [Figure 25] This is a longitudinal shrinkage distribution along the heating direction created from the prediction output data. [Figure 26] This is a longitudinal shrinkage distribution along the heating direction created from the prediction output data. [Figure 27] This is a longitudinal shrinkage distribution along the heating direction created from the prediction output data. [Figure 28] This is a longitudinal shrinkage distribution along the heating direction created from the prediction output data. [Figure 29] This is a vertical bending distribution along the heating direction created from the prediction output data. [Figure 30] This is a vertical bending distribution along the heating direction created from the prediction output data. [Figure 31] This is a vertical bending distribution along the heating direction created from the prediction output data. [Figure 32] This is a vertical bending distribution along the heating direction created from the prediction output data. DETAILED DESCRIPTION OF THE INVENTION

[0008] The prediction method of the present invention is a prediction method for predicting the plastic strain distribution (intrinsic strain distribution), residual stress distribution, or deformation of a target object, and includes a step of outputting prediction output data corresponding to the plastic strain distribution from prediction input data including heating conditions using a machine learning model trained with teacher data including learning input data including heating conditions and learning output data corresponding to the plastic strain distribution calculated from the heating conditions using a numerical analysis method.

[0009] The prediction method of the present invention preferably includes a step of calculating a deformation or residual stress distribution from the prediction output data, thereby making it possible to predict the deformation or residual stress distribution in a short time with high accuracy. It is preferable that the heating conditions included in the learning input data include at least one of bead-on welding, groove welding, fillet welding, plug welding, slot welding, multi-layer welding, metal additive manufacturing, strain relief by heating, cutting by heating, and bending by heating. The present invention also provides a prediction method for predicting the inherent deformation distribution along the heating direction of a target object, the prediction method including a step of outputting prediction output data corresponding to the inherent deformation distribution along the heating direction from prediction input data including heating conditions using a machine learning model trained with teacher data including learning input data including heating conditions and learning output data corresponding to the inherent deformation distribution along the heating direction calculated from the heating conditions using a numerical analysis method. The present invention also provides a program configured to cause a computer to execute the prediction method of the present invention.

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The configurations shown in the drawings and the following description are examples, and the scope of the present invention is not limited to those shown in the drawings and the following description.

[0011] First embodiment FIG. 1 is an explanatory diagram of the prediction method of this embodiment. The prediction method of the first embodiment is a prediction method for predicting the plastic strain distribution (inherent strain distribution), residual stress distribution, or deformation of a target object. The prediction method of this embodiment includes a step of outputting prediction output data corresponding to the plastic strain distribution from prediction input data including heating conditions using a machine learning model trained with training data including training input data including heating conditions and training output data corresponding to the plastic strain distribution (inherent strain distribution) calculated from the heating conditions using a numerical analysis method. The prediction method of this embodiment can also include a step of calculating the deformation or residual stress distribution from the prediction output data. The prediction method of this embodiment is a prediction method for predicting the plastic strain distribution, residual stress distribution, or deformation of a target object caused by, for example, bead-on welding, groove welding, fillet welding, plug welding, slot welding, multi-layer welding, metal additive manufacturing, strain relief by heating, cutting by heating, and bending by heating. The program of this embodiment is provided to cause a computer to execute the prediction method of this embodiment.

[0012] First, the creation of a machine learning model used in the prediction method of this embodiment will be described. Numerical analysis is used to create the training data. Examples of numerical analysis methods include thermo-elastic-plastic analysis, elasto-plastic analysis, and elastic analysis, and it is preferable to use thermo-elastic-plastic analysis. Thermo-elastic-plastic analysis can also include heat conduction analysis. Idealized explicit FEM can be used for thermo-elastic-plastic analysis. In the following explanation, training data is created using thermo-elastic-plastic analysis. Specifically, as shown in Figure 1, analysis is performed using geometric data (mesh data, etc.) (analysis model) of the target object, information on the target object's material (specific heat, density, thermal conductivity coefficient, Young's modulus, yield stress, Poisson's ratio, linear expansion coefficient, work hardening coefficient, etc.), and heating conditions (specifically, heat input, heat source distribution parameters, heating rate, coordinates of the heating start point, coordinates of the heating end point, etc.), and data corresponding to the plastic strain distribution (intrinsic strain distribution) is calculated. Furthermore, residual stress distribution or inherent deformation can be calculated as necessary. The "heat source distribution parameters" correspond to the standard deviation σ when the heat source distribution is assumed to be a normal distribution. "Plastic strain" includes strain that occurs when a target object is cooled after being locally melted or locally heated by welding, etc. "Plastic strain" may be "intrinsic strain" or "permanent strain." "Plastic strain" may also be "strain" that results from a numerical analysis. The heating conditions may also include at least one of bead-on welding, groove welding, fillet welding, seam welding, plug welding, slot welding, multi-layer welding, multi-pass welding, metal additive manufacturing (e.g., 3D printer, 3D metal additive manufacturing), strain relief by heating, cutting by heating (e.g., melt cutting), bending by heating (e.g., linear heating), and thermal spraying. In addition, the shape data (analysis model) of the target object can be shape data of any one of a butt joint, lap joint, double-sided pad joint, single-sided pad joint, corner joint, T-joint, cross joint, edge joint, metal additive manufacturing, strain relief, and bending.

[0013] Such a thermo-elastic-plastic analysis is repeated while randomly changing the heating conditions, etc. For example, the thermo-elastic-plastic analysis can be repeated 1,000 times or more. For example, the thermo-elastic-plastic analysis can be repeated while randomly changing the heat input, heating rate, coordinates of the heating start point, and coordinates of the heating end point. The same shape data of the target object, information about the material of the target object, etc. can be used in repeated thermo-elastic-plastic analyses. The thermo-elastic-plastic analysis may also be repeated while changing the shape data of the target object or information about the material of the target object.

[0014] The geometric conditions indicating the heating position on the input side can be set as follows: When setting the variables for a one-dimensional problem, they can be set as shown in Figure 2 (unit of length is unified as [mm]). The basic information of the heating conditions is expressed as follows: Qnet: net heat quantity per unit length [kJ / s], Qhh: heat input parameter [J / mm 3 ], Speed: heating rate [mm / s], thickness: plate thickness [mm], sigma: heat source parameter σ [mm], SE_length: heating length can be used. To express the stiffness at the target point P, P_L1: shortest distance (parallel) to the end of the target point P, and P_L2: shortest distance (perpendicular) to the end of the target point P can be used. To express the influence of the heating direction, PS_vector: signed distance from the target point P to the start point S, and PE_vector: signed distance from the target point P to the end point E can be used. This makes it possible to characterize the diversity of strain distribution using geometric distances, etc. The heat input parameter is a parameter that indicates the magnitude of heat input, which is determined by the relationship between the heat input, heating rate, and plate thickness, and is expressed as (Q / v) / h 2 Here, Q is the heat input (W), v is the heating rate (mm / s), and h is the plate thickness (mm).

[0015] When setting the variables for a three-dimensional problem, they can be set as shown in Figure 3 (units of length are unified as [mm]). The basic information of the heating conditions is expressed as follows: Qnet: net heat quantity per unit length [kJ / s], Qhh: heat input parameter [J / mm 3], Speed: heating rate [mm / s], thickness: plate thickness [mm], sigma: heat source parameter σ [mm], SE_length: heating length. To express the stiffness at target point P, P_L1: shortest distance to the edge of target point P (parallel), P_L2: shortest distance to the edge of target point P (perpendicular), and P_L3: shortest distance (depth) to the edge of target point P can be used. To express the influence of the heating direction, PS_vector: signed distance from target point P to start point S, and PE_vector: signed distance from target point P to end point E can be used. To express the thermal influence near the start and end points, S_L1: shortest distance to the edge of start point S (parallel), S_L2: shortest distance to the edge of start point S (perpendicular), E_L1: shortest distance to the edge of end point E (parallel), E_L2: shortest distance to the edge of end point E (perpendicular), and TH_length: maximum workable length can be used. The distance from the heating center can be P_heatline_L2: the minimum distance (vertical) from the heated part of the target point P, P_heatline_R: the radius of the heated part of the target point P (≠ L2), P_depth: the depth from the heated surface of the target point P (≠ L3).

[0016] The input items (entered by the user) required for fillet welding as shown in Figure 4 are: Qnet: net heat per unit length [kJ / s], Speed: heating rate [mm / s], sigma: heat source parameter σ [mm], Xs, Ys, Zs: coordinates of the welding start point (x, y, z) [mm], Xe, Ye, Ze: coordinates of the welding end point (x, y, z) [mm], CAD data for the model, Thickness_plate: base material plate thickness [mm], Thickness_web: web plate thickness [mm], plate dimensions [mm]. These user-entered items are converted internally into geometric explanatory variables for machine learning.

[0017] Training data can be created from the input data and analysis results used in the repeated thermo-elastic-plastic analysis. For example, the training input data items for this training data include the shape data of the target object, heat source distribution parameters, heat input amount, heating rate, and coordinates of the heating start point and the heating end point, and the training output data (correct answer data) includes data corresponding to the plastic strain distribution (intrinsic strain distribution). The training data includes many pairs of training input data and training input data (correct answer data). The training input data may also include information about the material of the target object. Furthermore, if the shape data of the target object is the same in all thermo-elastic-plastic analyses, this shape data can be excluded from the training input data.If the heat source distribution parameters are the same in all thermo-elastic-plastic analyses, this heat source distribution parameters can be excluded from the training input data.

[0018] Next, a machine learning model can be created by training a machine learning framework using the created training data.

[0019] Next, the input data for prediction is input to the machine learning model, and output data for prediction is output. The input data for prediction is input data for which the correct answer data is unknown, and the machine learning model is used to predict the correct answer data (output data for prediction) from this input data. The data items of the input data for prediction can be the same as the data items of the input data for learning. The input data for prediction include, for example, shape data of the target object, heat source distribution parameters, heat input, heating rate, coordinates of the heating start point, and coordinates of the heating end point. These input data are input into a machine learning model, and data corresponding to the plastic strain distribution (intrinsic strain distribution) is output as output data for prediction. By creating a plastic strain distribution from this data, it is possible to know the plastic strain distribution predicted when heating is performed under the heating conditions of the input data for prediction.

[0020] For example, many candidate heating conditions can be created, and a machine learning model can be used to create a predicted plastic strain distribution (inherent strain distribution) from each heating condition. The most appropriate plastic strain distribution can then be selected, and overheating, such as welding, can be performed using heating conditions corresponding to the selected plastic strain distribution. The prediction method of this embodiment can create a predicted plastic strain distribution in a short time, allowing for the setting of many candidate heating conditions and the identification of more appropriate heating conditions. Furthermore, even if the target object has a complex shape, a predicted plastic strain distribution can be created in a short time.

[0021] The prediction method of this embodiment can also include a step of calculating deformation from prediction output data (data corresponding to plastic strain distribution). The deformation can be calculated by integrating the plastic strain distribution (intrinsic strain distribution). For example, the inherent deformation (longitudinal shrinkage, longitudinal bending, transverse shrinkage, transverse bending) can be calculated from data corresponding to the plastic strain distribution using the relational equation shown in FIG. 5. This makes it possible to know the inherent deformation predicted when heated under the heating conditions of the prediction input data. The prediction method of this embodiment can calculate the predicted inherent deformation in a short time, making it possible to set many candidate heating conditions and find more appropriate heating conditions. Furthermore, even if the target object has a complex shape, the predicted inherent deformation can be calculated in a short time.

[0022] The prediction method of this embodiment may also include a step of performing elastic analysis using prediction output data (data corresponding to the plastic strain distribution) to calculate data corresponding to the residual stress distribution. A residual stress distribution can be created from this data corresponding to the residual stress distribution. For example, data corresponding to the plastic strain distribution (intrinsic strain distribution) (output data of the machine learning model) can be provided to a stress-free analytical model and elastic analysis can be performed to calculate data corresponding to the residual stress distribution. The prediction method of this embodiment can create a predicted residual stress distribution in a relatively short time, allowing for the setting of many candidate heating conditions and the identification of more appropriate heating conditions. Furthermore, even if the target object has a complex shape, a predicted residual stress distribution can be created in a short time. The prediction method of the first embodiment is effective when a comprehensive judgment is desired because it is possible to predict the plastic strain distribution, the inherent deformation distribution, and the residual stress distribution.

[0023] Second embodiment The prediction method of the second embodiment is a prediction method for predicting the inherent deformation distribution along the heating direction of a target object, and includes a step of outputting prediction output data corresponding to the inherent deformation distribution along the heating direction from prediction input data including heating conditions using a machine learning model trained with teacher data including learning input data including heating conditions and learning output data corresponding to the inherent deformation distribution along the heating direction calculated from the heating conditions using a numerical analysis method.

[0024] In the second embodiment, training data is created from input data and analysis results used in repeated thermo-elastic-plastic analyses, similar to the first embodiment, except that in the thermo-elastic-plastic analyses, training output data corresponding to the inherent deformation distribution along the heating direction is calculated. Next, a machine learning model can be created by training a machine learning framework using the created training data. Next, the prediction input data is input to the machine learning model, and the prediction output data is output. The input data for prediction include, for example, shape data of the target object, heat source distribution parameters, heat input, heating rate, coordinates of the heating start point, and coordinates of the heating end point. These input data are input into a machine learning model, and data corresponding to the intrinsic deformation distribution along the heating direction (angular distortion distribution, lateral shrinkage distribution, longitudinal shrinkage distribution, longitudinal bending distribution) is output as output data for prediction. By creating an intrinsic deformation distribution from this data, it is possible to know the intrinsic deformation distribution predicted when heating is performed under the heating conditions of the input data for prediction. The prediction method of the second embodiment is effective when you want to know only the inherent deformation distribution. The inherent deformation distribution has only four components (longitudinal shrinkage, longitudinal bending, transverse shrinkage, and transverse bending) for each cross section, so there is little freedom in obtaining its distribution in the heating line direction (about 100 components), and it can be predicted relatively easily.

[0025] Creating a machine learning model 1 A thermo-elastic-plastic analysis was performed to create training data, and a machine learning model was created using this training data.Thermal-elastic-plastic analysis was performed using an idealized explicit FEM. Figure 6 is a schematic diagram of the analytical model (shape data of the target object) used in the thermo-elastic-plastic analysis. The target object is a steel plate with a length of 400 mm, a width of 400 mm, and a thickness of 16 mm. The longitudinal direction of the analytical model is the x-direction, the lateral direction of the analytical model is the y-direction, and the thickness direction of the analytical model is the z-direction. The analytical model is divided into multiple elements (mesh), and each vertex of each element is a node. In addition, the analytical model has an area with a width of 80 mm and a length of 400 mm, centered on a line (a line extending in the x-direction) connecting the midpoints of the two sides of the analytical model extending in the y-direction, which is divided into elements with a mesh size of 2.5 mm.

[0026] Using this analytical model, 3,900 thermo-elastic-plastic analyses were performed under various heating conditions (gas heating), and data corresponding to the plastic strain distribution were calculated for each analysis. In all analyses, the thermal efficiency was set to 1.0, and the heat source distribution parameter σ was set to 20 mm. The starting and ending points of the heating line in each analysis were randomly set on a line connecting the midpoints of the two sides of the analysis model extending in the y direction (a line extending in the x direction). The heat input in each analysis was randomly set within a range of 2,000 W to 40,000 W (2 kW to 40 kW). The heating rate in each analysis was randomly set within a range of 1 mm / sec to 20 mm / sec. In addition, to represent the start point and end point of the heating line on the line connecting the midpoints of two sides extending in the y direction of the analytical model, an x-coordinate is used, with one end of the line connecting the midpoints being 0 and the other end being 400 (0 → 400 is the x-direction).

[0027] Based on the results of 3,900 thermal elastic-plastic analyses, training data was created in which the data items of the learning input data were the shape data of the target object, heat source distribution parameters, heat input, starting and ending points of the heating line, and heating rate, and the learning output data was data corresponding to the plastic strain distribution.This training data was used to train a machine learning framework and create a machine learning model.

[0028] Calculation of plastic strain distribution and inherent strain The prediction input data (shape data of the target object, heat source distribution parameter σ: 20 mm, heat input: 10,000 W (10 kW), x-coordinate of starting point: 0, x-coordinate of ending point: 400, heating rate: 2 mm / sec) was input into the created machine learning model, and prediction output data (data corresponding to the plastic strain distribution) was output. Figure 7(b) shows the plastic strain distribution (predicted distribution) in the x-direction (vertical direction) created from this prediction output data. Figure 7(a) shows the plastic strain distribution in the x direction created from the results of a thermal elastic-plastic analysis (heat source distribution parameter σ: 20 mm, heat input: 10,000 W (10 kW), x coordinate of starting point: 0, x coordinate of ending point: 400, heating rate: 2 mm / sec, analysis model: same as above). In addition, prediction input data (shape data of the target object, heat source distribution parameter σ: 20 mm, heat input: 10,000 W (10 kW), x-coordinate of starting point: 0, x-coordinate of ending point: 400, heating rate: 4 mm / sec) was input into the created machine learning model, and prediction output data (data corresponding to the plastic strain distribution) was output. Figure 8(b) shows the plastic strain distribution (predicted distribution) in the x-direction (vertical direction) created from this prediction output data. Figure 9(b) shows the plastic strain distribution (predicted distribution) in the y-direction (horizontal direction) created from this prediction output data. Figure 8(a) shows the plastic strain distribution in the x direction created from the results of a thermo-elastic-plastic analysis (heat source distribution parameter σ: 20 mm, heat input: 10,000 W (10 kW), x-coordinate of starting point: 0, x-coordinate of ending point: 400, heating rate: 4 mm / sec, analytical model: same as above). Figure 9(a) shows the plastic strain distribution in the y direction created from the results of this thermo-elastic-plastic analysis. As shown in Figures 7 to 9, it was found that the plastic strain distribution (predicted distribution) created from the output data of the machine learning model was in good agreement with the plastic strain distribution created from the results of the thermal elastic-plastic analysis.

[0029] Next, using the relationship between inherent deformation and inherent strain shown in Figure 5, the four components of inherent deformation (longitudinal shrinkage, transverse shrinkage, longitudinal bending, transverse bending) were calculated from the data corresponding to the plastic strain distribution shown in Figures 7(b), 8(b), and 9(b) (output data of the machine learning model). Additionally, using thermo-elastic-plastic analysis, the inherent deformations (longitudinal shrinkage, transverse shrinkage, longitudinal bending, transverse bending) corresponding to the plastic strain distributions shown in Figures 7(a), 8(a), and 9(a) were calculated. Figures 10(a) to 10(d) are graphs comparing the inherent deformation calculated using the relational equation in Figure 5 (labeled "Prediction") with the inherent deformation calculated using thermo-elastic-plastic analysis (labeled "Thermal-elastic-plastic analysis"). As shown in the graphs in Figures 10(a) to 10(d), it was found that the four inherent deformation components calculated from the output data of the machine learning model were in good agreement with the four inherent deformation components calculated using thermal elastic-plastic analysis.

[0030] Next, the prediction input data (shape data of the target object, heat source distribution parameter σ: 20 mm, heat input: 10,000 W (10 kW), x-coordinate of starting point: 200, x-coordinate of ending point: 400, heating rate: 4 mm / sec) was input into the created machine learning model, and prediction output data (data corresponding to the plastic strain distribution) was output. Figure 11(b) shows the plastic strain distribution (predicted distribution) in the x-direction (vertical direction) created from this prediction output data. Figure 12(b) shows the plastic strain distribution (predicted distribution) in the y-direction (horizontal direction) created from this prediction output data. Figure 11(a) shows the plastic strain distribution in the x direction created from the results of a thermo-elastic-plastic analysis (heat source distribution parameter σ: 20 mm, heat input: 10,000 W (10 kW), x-coordinate of starting point: 200, x-coordinate of ending point: 400, heating rate: 4 mm / sec, analytical model: same as above). Figure 12(a) shows the plastic strain distribution in the y direction created from the results of this thermo-elastic-plastic analysis. As shown in Figures 11 and 12, the plastic strain distribution (predicted distribution) created from the output data of the machine learning model was found to be in good agreement with the plastic strain distribution created from the results of the thermo-elastic-plastic analysis.

[0031] Next, using the relationship between inherent deformation and inherent strain shown in Figure 5, the four components of inherent deformation (longitudinal shrinkage, transverse shrinkage, longitudinal bending, transverse bending) were calculated from the data corresponding to the plastic strain distribution shown in Figure 11(b) and Figure 12(b) (output data of the machine learning model). Furthermore, using thermo-elastic-plastic analysis, the inherent deformations (longitudinal shrinkage, transverse shrinkage, longitudinal bending, transverse bending) corresponding to the plastic strain distributions shown in Figure 11(a) and Figure 12(a) were calculated. Figures 13(a) to 13(d) are graphs comparing the inherent deformation calculated using the relational equation in Figure 5 (labeled "Prediction") with the inherent deformation calculated using thermo-elastic-plastic analysis (labeled "Thermal-elastic-plastic analysis"). As shown in the graphs in Figures 13(a) to 13(d), it was found that the four inherent deformation components calculated from the output data of the machine learning model were in good agreement with the four inherent deformation components calculated using thermal elastic-plastic analysis.

[0032] Calculation of plastic strain distribution, inherent strain and residual stress distribution Using analytical models of T-joints (shape data of the target object) such as those shown in Figures 14(a)(b) and 15(a)(b), thermo-elastic-plastic analyses were performed multiple times under various heating conditions (gas heating for back-side strain relief), and data corresponding to the plastic strain distribution was calculated for each thermo-elastic-plastic analysis. An idealized explicit FEM method was used for the thermo-elastic-plastic analysis. The target object had a shape in which a steel plate measuring 400 mm in length, 400 mm in width, and 16 mm in thickness was welded to another steel plate measuring 400 mm in length, 84 mm in width, and 15 mm in thickness in a T-shape. In all thermo-elastic-plastic analyses, the thermal efficiency was set to 1.0, and the heat source distribution parameter σ was set to 20 mm. The starting and ending points of the heating lines in each thermo-elastic-plastic analysis were randomly set on a line connecting the midpoints of the two sides extending in the y direction of the analysis model (a line extending in the x direction). The heat input in each thermo-elastic-plastic analysis was randomly set within a range of 2000 W to 40,000 W (2 kW to 40 kW). The heating rate in each thermo-elastic-plastic analysis was randomly set within a range of 1 mm / sec to 20 mm / sec. Based on the results of the thermal elastic-plastic analysis, training data was created in which the data items of the learning input data were the shape data of the target object, heat source distribution parameters, heat input, starting and ending points of the heating line, and heating rate, and the learning output data was data corresponding to the plastic strain distribution.This training data was used to train a machine learning framework and create a machine learning model.

[0033] Next, the prediction input data (heat source distribution parameter σ: 20 mm, heat input: 10,000 W (10 kW), x-coordinate of starting point: 0, x-coordinate of ending point: 400, heating rate: 2 mm / sec) was input into the created machine learning model, and prediction output data (data corresponding to the plastic strain distribution) was output. Figure 14(b) shows the plastic strain distribution in the x-direction (vertical direction) created from this prediction output data. Figure 14(a) shows the plastic strain distribution in the x direction created from the results of a thermal elastic-plastic analysis (heat source distribution parameter σ: 20 mm, heat input: 10,000 W (10 kW), x coordinate of starting point: 0, x coordinate of ending point: 400, heating rate: 2 mm / sec, analytical model: the above-mentioned T-joint analytical model). As shown in Figure 14(a)(b), even when the target object is a T-joint, the plastic strain distribution created from the output data of the machine learning model was found to be in good agreement with the plastic strain distribution created from the results of the thermo-elastic-plastic analysis.

[0034] Next, data corresponding to the plastic strain distribution shown in Fig. 14(b) (output data of the machine learning model) was fed to the stress-free analytical model and elastic analysis was performed to calculate data corresponding to the residual stress distribution in the x direction. Fig. 15(b) shows the residual stress distribution in the x direction created from the calculated data. Figure 15(a) shows the residual stress distribution in the x direction created from the results of a thermal elastic-plastic analysis (heat source distribution parameter σ: 20 mm, heat input: 10,000 W (10 kW), x coordinate of starting point: 0, x coordinate of ending point: 400, heating rate: 2 mm / sec, analysis model: the above-mentioned T-joint analysis model). As shown in Figure 15(a)(b), even when the target object is a T-joint, the residual stress distribution created from the output data of the machine learning model was found to be in good agreement with the residual stress distribution created from the results of the thermal elastic-plastic analysis.

[0035] Next, using the relationship between inherent deformation and inherent strain shown in Figure 5, the inherent deformation (longitudinal shrinkage, transverse bending (angular deformation)) was calculated from the data corresponding to the plastic strain distribution shown in Figure 14(b) (output data of the machine learning model). Furthermore, the inherent deformation (longitudinal shrinkage and transverse bending (angular distortion)) corresponding to the plastic strain distribution shown in Figure 14(a) was calculated using thermo-elastic-plastic analysis. Figures 16(a) and 16(b) are graphs comparing the inherent deformation calculated using the relational equation in Figure 5 (labeled "Prediction") with the inherent deformation calculated using thermo-elastic-plastic analysis (labeled "Thermal-elastic-plastic analysis"). As shown in the graphs in Figure 16(a) and (b), even when the target object is a T-joint, the inherent deformation calculated from the output data of the machine learning model was found to be in good agreement with the inherent deformation calculated using thermal elastic-plastic analysis.

[0036] Creating a machine learning model 2 A thermo-elastic-plastic analysis was performed to create training data, and a machine learning model was created using this training data.Thermal-elastic-plastic analysis was performed using an idealized explicit FEM. The analytical model used was the same as that used in "Creating a Machine Learning Model 1" (analysis model in Figure 6). Using this analytical model, thermo-elastic-plastic analyses were repeatedly performed under various heating conditions (gas heating), and data corresponding to deformation (angular distortion, transverse shrinkage, longitudinal shrinkage, longitudinal bending) was calculated for each thermo-elastic-plastic analysis. The heating conditions were set in the same way as in "Creating a Machine Learning Model 1." Based on the results of the thermal elastic-plastic analysis, training data was created in which the data items of the learning input data were the shape data of the target object, heat source distribution parameters, heat input, starting and ending points of the heating line, and heating rate, and the learning output data was data corresponding to the inherent deformation distribution along the heating direction (angular distortion distribution, transverse shrinkage distribution, longitudinal shrinkage distribution, longitudinal bending distribution).This training data was used to train a machine learning framework and create a machine learning model.

[0037] The input data for prediction (shape data of the target object, heat source distribution parameters, heat input: 20,000 W (20 kW), x-coordinate of the starting point, x-coordinate of the ending point, heating rate) was input into the created machine learning model, and the output data for prediction (data corresponding to the inherent deformation distribution along the heating direction) was output. 17 to 20 show angular distortion distributions created from the prediction output data. In Fig. 17, the x-coordinate of the start point is 0 and the x-coordinate of the end point is 400. In Fig. 18, the x-coordinate of the start point is 100 and the x-coordinate of the end point is 300. In Fig. 19, the x-coordinate of the start point is 100 and the x-coordinate of the end point is 350. In Fig. 20, the x-coordinate of the start point is 100 and the x-coordinate of the end point is 400. In addition, the heat input parameter Qhh [J / mm 3 ] and heating rate Speed ​​[mm / s] are shown in each figure. Qhh is (Q / v) / h 2 where Q is the heat input (W), v is the heating rate (mm / s), and h is the plate thickness (mm).

[0038] 21 to 24 show the distribution of the amount of transverse shrinkage created from the output data for prediction. In FIG. 21, the x-coordinate of the start point is 0 and the x-coordinate of the end point is 400. In FIG. 22, the x-coordinate of the start point is 100 and the x-coordinate of the end point is 300. In FIG. 23, the x-coordinate of the start point is 100 and the x-coordinate of the end point is 350. In FIG. 24, the x-coordinate of the start point is 100 and the x-coordinate of the end point is 400. In addition, the heat input parameter Qhh [J / mm 3 ] and heating speed [mm / s] are shown in each figure.

[0039] 25 to 28 show the distribution of the amount of transverse shrinkage created from the output data for prediction. In FIG. 21, the x coordinate of the start point is 0 and the x coordinate of the end point is 400. In FIG. 22, the x coordinate of the start point is 100 and the x coordinate of the end point is 300. In FIG. 23, the x coordinate of the start point is 100 and the x coordinate of the end point is 350. In FIG. 24, the x coordinate of the start point is 100 and the x coordinate of the end point is 400. In addition, the heat input parameter Qhh [J / mm 3 ] and heating speed [mm / s] are shown in each figure.

[0040] 29 to 32 show longitudinal shrinkage distributions created from the prediction output data. In FIG. 29, the x-coordinate of the start point is 0 and the x-coordinate of the end point is 400. In FIG. 30, the x-coordinate of the start point is 100 and the x-coordinate of the end point is 300. In FIG. 31, the x-coordinate of the start point is 100 and the x-coordinate of the end point is 350. In FIG. 32, the x-coordinate of the start point is 100 and the x-coordinate of the end point is 400. In addition, the heat input parameter Qhh [J / mm 3 ] and heating speed [mm / s] are shown in each figure. 17 to 32, it was found that the inherent deformation distribution along the heating direction can be predicted well.

Claims

1. A prediction method for predicting an angular distortion distribution in a heating line direction, a transverse shrinkage distribution in a heating line direction, a longitudinal shrinkage distribution in a heating line direction, and a longitudinal bending distribution in a heating line direction of an object, comprising: The prediction method includes a step of outputting prediction output data corresponding to the angular distortion distribution in the heating line direction, the transverse shrinkage distribution in the heating line direction, the longitudinal shrinkage distribution in the heating line direction, and the longitudinal bending distribution in the heating line direction from the prediction input data including the heating conditions including the starting point and the end point of the heating line, using a machine learning model trained with teacher data including training input data including heating conditions including the starting point and the end point of the heating line, and training output data corresponding to the angular distortion distribution in the heating line direction, the transverse shrinkage distribution in the heating line direction, the longitudinal shrinkage distribution in the heating line direction, and the longitudinal bending distribution in the heating line direction, calculated from the heating conditions using a numerical analysis method.

2. A program configured to cause a computer to execute the prediction method according to claim 1.

Images